Adaptive layout of user interface, method and apparatus for determining optimal user interface

Abstract

This invention discloses an adaptive layout for a user interface, a method for determining the optimal user interface, and an apparatus. The method includes acquiring user behavior data of multiple users within a first preset historical time period, device information of the devices used by each user, and UI element data of the current system on the corresponding device; based on the user behavior data and device information of each user, obtaining different types of first behavior patterns; each first behavior pattern represents the user's single-action operation preference; processing the various first behavior patterns to obtain multiple second behavior patterns, each second behavior pattern representing the user's continuous-action operation preference; based on the multiple second behavior patterns and UI element data of the current system on the corresponding device, drawing multiple interface layouts and saving them; each interface layout represents the optimal layout under the second behavior patterns on a device. This method can automatically adjust the interface layout to achieve a personalized and adapted user interface.

Description

Technical Field

[0001] This invention relates to the field of computer science and technology, and in particular to an adaptive layout of a user interface, a method and apparatus for determining the optimal user interface. Background Technology

[0002] In software and web application development, user interface (UI) design and optimization are crucial. An intuitive, user-friendly, and aesthetically pleasing UI can significantly improve user satisfaction and loyalty, thereby impacting a product's market competitiveness. However, with the rapid development of mobile devices and internet technology, UI design faces several challenges: 1. The challenge of device diversity: The current market offers a wide variety of devices, from smartphones and tablets to laptops, desktops, smart TVs, and wearable devices, each with its unique screen size, resolution, and interaction methods. This requires user interface design to be not only aesthetically pleasing but also adaptable to various display environments and user operating habits; 2. Challenges brought by the complexity of user behavior: User behavior patterns are diverse, and different users have different usage habits and preferences. Some users may prefer a simple interface, while others may prefer a feature-rich layout. In addition, user behavior changes with time and environment, which requires the user interface to have a certain degree of flexibility and adaptability; 3. Limitations of manual optimization: Traditional user interface optimization mainly relies on the developer's experience and intuition, as well as user feedback. Developers need to manually adjust the layout, font size, color scheme, etc., to adapt to different devices and user needs. This method is not only time-consuming and labor-intensive, but it is also difficult to guarantee that the optimization results can meet the needs of all users; 4. Data-driven optimization needs: With the development of big data technology, more and more companies are beginning to use user behavior data to guide product design and optimization. By analyzing user clicks, swipes, dwell time, and other behavioral data, users' needs and preferences can be understood more accurately, thereby designing user interfaces that better meet user expectations; In conclusion, although traditional user interface design and optimization methods are still effective in some cases, they have shown obvious limitations in the face of device diversity, user behavior complexity, and data-driven optimization needs. Therefore, developing a front-end user interface adaptive optimization system can not only improve the efficiency and quality of UI design, but also provide users with a more personalized and high-quality interactive experience, which has important practical application value and market prospects. Summary of the Invention

[0003] The current market offers a wide variety of devices, each with different screen sizes, resolutions, and interaction methods. Simply relying on developers to manually adjust the interface layout is no longer sufficient to meet the demands of quickly and efficiently adapting to various devices. Furthermore, traditional methods that rely on developers manually adjusting the interface layout cannot meet the personalized interface layout requirements of users. The inventors of this invention have discovered that the development of artificial intelligence (AI) technology has provided new possibilities for the automated and intelligent optimization of user interfaces. AI algorithms can automatically analyze user behavior data, learn user preferences, and automatically adjust the layout and elements of the user interface accordingly, achieving personalized user experience optimization.

[0004] In view of the above problems and findings, the present invention is proposed to provide an adaptive layout of a user interface, a method and apparatus for determining an optimal user interface that overcomes or at least partially solves the above problems.

[0005] In a first aspect, embodiments of the present invention provide an adaptive layout method for a user interface, comprising:

[0006] Obtain user behavior data of multiple users within a first preset historical time period, as well as device information of the devices used by each user and UI element data of the current system on the corresponding device;

[0007] Based on the user behavior data of each user and the device information of the device used by each user, different types of first behavior patterns are obtained; the first behavior pattern represents the user's operation preference for a single action.

[0008] The various first behavior patterns are processed to obtain multiple second behavior patterns, and the second behavior patterns represent the user's operational preferences for continuous actions.

[0009] Based on the multiple second behavior modes and the UI element data of the current system on the corresponding device, multiple interface layouts are drawn and saved; the interface layout represents the optimal layout on the device under the second behavior mode.

[0010] In one embodiment, the different types of first behavior patterns obtained based on user behavior data for each user and device information for each device include:

[0011] Perform data cleaning and formatting on the user behavior data of each user;

[0012] For each user's processed user behavior data and the device information of the device used by each user, a sequence analysis method is used to obtain the first behavior pattern corresponding to each user behavior data. The device information includes device type, screen size, and screen resolution.

[0013] Classify the primary behavioral patterns;

[0014] A clustering algorithm is used to obtain different types of first behavior models based on the classified first behavior patterns. Each type has multiple first behavior patterns.

[0015] In one embodiment, processing various first behavior patterns to obtain multiple second behavior patterns includes:

[0016] By employing recurrent neural networks and long short-term memory networks, the time-series characteristics of each first behavioral pattern under various categories are processed to obtain the second behavioral pattern corresponding to each category.

[0017] In one embodiment, drawing multiple interface layouts based on the plurality of second behavior patterns and the UI element data of the current system on the corresponding device includes:

[0018] For each of the second behavior modes, based on the second behavior mode and the device information in the second behavior mode, adjust the UI element data of the current system on the corresponding device in each second behavior mode, and draw the interface layout of each second behavior mode on different devices.

[0019] In one embodiment, the method further includes:

[0020] Collect feedback data from each user within the first preset historical time period;

[0021] For each user, based on the user's feedback data, adjust the UI element data of the device used by the user.

[0022] Secondly, embodiments of the present invention provide a method for determining an optimal user interface, comprising:

[0023] Get current device information and data of various UI elements within the current application;

[0024] Collect current user behavior data within a second preset historical time period, and process the current user behavior data;

[0025] Based on the processed current user behavior data, current device information, and UI element data, the optimal user interface is matched from a variety of saved interface layouts.

[0026] In one embodiment, after matching the optimal user interface, the method further includes:

[0027] Collect feedback data from the current user within a second preset historical time period;

[0028] Based on the feedback data, the UI element data in the optimal user interface is adjusted, and the adjusted user interface is taken as the optimal user interface.

[0029] Thirdly, embodiments of the present invention provide an adaptive layout system for a user interface, comprising:

[0030] The data acquisition module is used to acquire user behavior data of multiple users within a first preset historical time period, as well as device information of the devices used by each user and UI element data of the current system on the corresponding device.

[0031] The data processing and data analysis module is used to obtain different types of first behavior patterns based on the user behavior data of each user and the device information of the devices used by each user; the first behavior pattern represents the user's operation preference for a single action.

[0032] The preference learning module is used to process each of the first behavior patterns to obtain multiple second behavior patterns, whereby the second behavior patterns represent the user's operational preferences for continuous actions.

[0033] The layout optimization module is used to draw multiple interface layouts based on the multiple second behavior modes and the UI element data of the current system on the corresponding device; the interface layout represents the optimal layout on the device under the second behavior mode.

[0034] Fourthly, embodiments of the present invention provide a computer storage medium storing computer-executable instructions, which, when executed by a processor, implement the aforementioned adaptive layout method for the user interface or the aforementioned method for determining the optimal user interface.

[0035] Fifthly, embodiments of the present invention provide a terminal device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the aforementioned adaptive layout method for the user interface or the aforementioned method for determining the optimal user interface.

[0036] The beneficial effects of the above-described technical solutions provided in the embodiments of the present invention include at least the following:

[0037] The adaptive layout method for user interfaces provided in this invention obtains a large amount of user behavior data from a first preset historical time period, as well as device information of each user's device. Based on the user behavior data and corresponding device information, a first behavior pattern representing a user's single-action operation preference is obtained. Next, each first behavior pattern is processed to obtain a second behavior pattern representing a user's continuous operation preference. Based on the second behavior pattern, i.e., based on the user's continuous operation preference, and the obtained UI element data of the current system, multiple interface layouts are drawn and saved. Each interface layout represents the optimal layout suitable for the second behavior pattern on a particular device. This fully considers that each user has their own unique usage habits and aesthetic preferences. By analyzing a large amount of user behavior data, the operation preferences of different users are extracted, and user operation preferences are learned. Based on these different operation preferences, personalized customization of the user interface is achieved, providing users with a more considerate and personalized interactive experience. Simultaneously, based on the obtained large amount of device information, the adaptive layout method for user interfaces can automatically adjust the UI element layout to better adapt to various devices, ensuring the consistency of the user interface across different devices.

[0038] In addition, embodiments of the present invention utilize recurrent neural networks and long short-term memory networks to process the time-series characteristics of each first behavioral pattern, learning to identify more complex behavioral patterns, namely second behavioral patterns. The first behavioral pattern represents the user's single-action operational preference, such as a user's click behavior; while the second behavioral pattern is the result of processing the time-series data of the first behavioral pattern. In other words, the second behavioral pattern represents the operational preference for continuous actions, such as a series of user actions during the browsing and purchase process of a product. This allows for personalized customization of the user interface based on user habits and preferences, eliminating reliance on developers' experience and intuition to adjust the layout. It automatically adjusts the interface layout to suit each user's different operational preferences.

[0039] In addition, by acquiring feedback data from each user, the system can directly adjust the UI elements of the user's device, such as the size, position, and color of a control, to achieve personalized interface layout for each user.

[0040] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings.

[0041] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0042] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0043] Figure 1 This is a flowchart of the adaptive layout method for the user interface in an embodiment of the present invention;

[0044] Figure 2 This is a flowchart illustrating the methods for obtaining different types of first behavior patterns in embodiments of the present invention;

[0045] Figure 3 This is a flowchart illustrating the method for determining the optimal user interface in an embodiment of the present invention.

[0046] Figure 4 This is one of the structural schematic diagrams of the adaptive layout system for the user interface in an embodiment of the present invention;

[0047] Figure 5 This is the second structural schematic diagram of the adaptive layout system for the user interface in an embodiment of the present invention. Detailed Implementation

[0048] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0049] To address the problem of existing technologies failing to achieve personalized and consistent user experiences across devices, embodiments of the present invention provide an adaptive layout of the user interface, a method and apparatus for determining the optimal user interface.

[0050] Example 1

[0051] Embodiment 1 of the present invention provides an adaptive layout method for a user interface, the process of which is as follows: Figure 1 As shown, it includes the following steps:

[0052] Step S101: Obtain user behavior data of multiple users within the first preset historical time period, as well as device information of the devices used by each user and UI element data of the current system on the corresponding device;

[0053] Step S102: Based on the user behavior data of each user and the device information of the device used by each user, different types of first behavior patterns are obtained; the first behavior pattern represents the user's operation preference for a single action;

[0054] Step S103: Process various first behavior patterns to obtain multiple second behavior patterns. The second behavior patterns represent the user's operational preferences for continuous actions.

[0055] Step S104: Based on multiple second behavior modes and the UI element data of the current system on the corresponding device, draw multiple interface layouts and save them; the interface layout represents the optimal layout on the device under the second behavior mode.

[0056] In step S101 above, tracking code is embedded in the current system to record user actions such as clicks, swipes, and form submissions in detail. Each action corresponds to a type of user behavior data. For example, embedding a selling point on the "Add to Cart" and "Buy Now" buttons on an e-commerce website allows tracking of user clicks on these two buttons. The current system can also collect data from multiple platforms such as PCs and mobile devices to ensure that user behavior can be collected regardless of the device they use. Methods for collecting user behavior data include:

[0057] (1) Event triggering: The current system involves a triggering mechanism that enables data to be automatically recorded when a user completes a specific action;

[0058] (2) Custom data collection: Customize data collection points according to business needs, such as tracking user interaction in specific ad slots.

[0059] The first preset historical time period can be 3 months or half a year, depending on the amount of user behavior data obtained;

[0060] Device information includes device type, device resolution, and screen size; UI element data includes UI control size information, position information, control attributes, and other data. The process of obtaining UI element data is actually a process of identifying and classifying UI elements. In addition, this embodiment of the invention also integrates natural language processing technology, enabling the current system to parse user text input and visual feedback to more comprehensively understand user behavior, provide a data basis for adjusting UI layout, and thus provide a more accurate personalized experience.

[0061] In some optional embodiments, in step S102 above, different types of first behavioral patterns are obtained, referring to... Figure 2 As shown, this can be achieved in the following way:

[0062] Step S201: Perform data cleaning and formatting on the user behavior data of each user;

[0063] Specifically, noise reduction, missing value filling, and data format standardization are performed on each user behavior data to ensure the quality and consistency of each user behavior data. For example, duplicate click data caused by current system errors are removed from the obtained user click behavior data.

[0064] Step S202: For the processed user behavior data of each user and the device information of the device used by each user, the sequence analysis method is used to obtain the first behavior pattern corresponding to each user behavior data. The device information includes device type, screen size and screen resolution.

[0065] For each user, based on the user's behavior data and the device information of the user's device, a sequence analysis method is used to analyze and identify the user behavior data to identify the first behavior pattern. The first behavior pattern represents the user's operation preference for a single action, such as "clicking", "swiping", "inputting" etc.

[0066] Step S203: Classify each first behavior pattern;

[0067] A supervised learning classification algorithm is used to classify each first behavior pattern;

[0068] Step S204: Using a clustering algorithm, based on the classified first behavior patterns, different types of first behavior models are obtained, with multiple first behavior patterns under each type.

[0069] After classification, in order to ensure that there is a sufficient amount of data on the first behavior pattern in each category, a clustering algorithm can be used to further group the classified first behavior patterns to identify the first behavior patterns with similar characteristics among users.

[0070] In some optional embodiments, step S103 above can be implemented in the following manner:

[0071] By employing recurrent neural networks and long short-term memory networks, the time-series characteristics of each first behavior pattern under various categories are processed to obtain the second behavior pattern corresponding to each category.

[0072] The first behavioral pattern represents a single action. In time, multiple first behavioral patterns form a complex set of actions. In fact, by using deep learning technology to process the time-series characteristics of each first behavioral pattern, complex behavioral patterns, namely the second behavioral pattern, can be identified. The second behavioral pattern represents the operational preference of continuous actions. For example, Long Short-Term Memory (LSTM) networks can identify the correlation between different first behavioral patterns. In other words, LSTM networks can be used to predict the user's behavioral path in completing a certain process. Taking advantage of this advantage, the embodiments of the present invention can complete the task of predicting user behavior, such as predicting the user's behavioral path in the process of "completing a purchase", so as to preload the page content pointed to by the link, thereby reducing loading time and improving response speed.

[0073] In addition, by introducing automated artificial intelligence algorithms, the efficiency of user interface design and optimization is greatly improved. Compared to the traditional design process that requires designers to manually adjust and test multiple layouts, this invention can automatically complete the adjustment of UI elements.

[0074] In one embodiment, step S104 can be implemented in the following manner:

[0075] For each second behavior pattern, based on the second behavior pattern and the device information in the second behavior pattern, adjust the UI element data of the current system on the corresponding device in each second behavior pattern, and draw the interface layout of each second behavior pattern on different devices.

[0076] Specifically, based on the obtained second behavior pattern and the obtained UI element data, the UI layout is adjusted. By closely integrating user behavior data with UI optimization, user needs can be grasped more accurately, and more targeted user experience optimization solutions can be provided, namely, user interface design that is more suitable for user operating habits. This adapts to the unique needs and preferences of each user, and significantly improves the user experience through personalized user interface design, thereby providing a more considerate and user-friendly interactive experience.

[0077] In addition, based on device information in the second behavior mode, such as screen size, screen resolution, screen orientation, and operating system, the UI layout and elements are automatically adjusted using responsive design technology to ensure that content is displayed optimally on different devices. For example, for touchscreen devices, the current system can optimize the size and spacing of touch targets to improve touch accuracy. The current system will also dynamically adjust the layout based on the user's interaction mode, such as one-handed operation or landscape use, to improve usability and comfort.

[0078] Especially today, with the increasing prevalence of multi-device use, maintaining a consistent user interface across different devices is crucial for enhancing user experience. This invention automatically adapts to the screen size and resolution of different devices, ensuring a consistent experience for users on any device, thus enhancing brand consistency and professionalism.

[0079] Furthermore, the adaptive layout method for user interfaces provided in this invention lowers the technical barrier for front-end developers in UI design. Even non-professional developers can use this adaptive layout method to design high-quality user interfaces, thus expanding the talent pool for front-end development.

[0080] In some optional embodiments, the method further includes:

[0081] (1) Collect feedback data from each user within the first preset historical time period;

[0082] (2) For each user, adjust the UI element data of the user's device based on the user's feedback data.

[0083] Specifically, the current system provides a button on the current page. Clicking this button enters developer mode, where users can obtain information such as the size and position of various controls on the current page, allowing them to accurately select the controls that need feedback. Users can also input their suggestions for adjusting the space requiring feedback in the feedback window provided on the page. The system then receives the user's feedback and directly adjusts the control accordingly, ensuring that the optimization measures address the user's actual problems and improve user satisfaction.

[0084] For example, if multiple users report that a certain feature is difficult to find or use, the system can trigger an optimization process that automatically adjusts the visibility and ease of use of that feature.

[0085] This invention not only focuses on the automation and intelligence of UI design but also considers the in-depth analysis and application of user behavior data. By closely integrating user behavior data analysis with UI optimization, user needs can be grasped more accurately, providing more targeted user experience optimization solutions. The feedback mechanism allows users to directly participate in the UI design optimization process, collecting and analyzing user feedback in real time, and using the feedback to guide subsequent UI optimizations. This sense of participation and control significantly improves user satisfaction and loyalty, enhancing not only the user experience but also providing strong support for the automation and intelligence of the front-end development process, demonstrating broad application prospects and commercial value.

[0086] Example 2

[0087] Embodiment 1 of the present invention provides a method for determining the optimal user interface, the process of which is as follows: Figure 3 As shown, it includes the following steps:

[0088] Step S301: Obtain current device information and data of each UI element within the current application;

[0089] Step S302: Collect current user behavior data within the second preset historical time period and process the current user behavior data;

[0090] Step S303: Based on the processed current user behavior data, current device information, and UI element data, the optimal user interface is matched from the various saved interface layouts.

[0091] The optimal user interface determination method provided in Embodiment 2 of this invention is applicable to the following scenario: a system that needs to implement user interface adaptive functionality (hereinafter referred to as the target system for ease of explanation). By introducing the user interface adaptive layout method provided in this embodiment of the invention, a user interface suitable for each user's operating habits and preferences can be provided for different users using the target system. Specifically, when a user downloads the target system for the first time, since the target system does not know the user's behavior habits, it provides the user with an initial page. After the user uses the target system for a period of time, by collecting user behavior data during this period, the user's usage habits and preferences are analyzed. Based on the analysis results, the interface layout that best matches the user's usage habits and preferences is matched from the various interface layouts stored by the target system, and this is taken as the optimal user interface. If no interface layout that matches the user's usage habits and preferences can be matched, the target system generates an interface layout that matches the user's usage habits and preferences based on the user behavior data collected during this period, and this is taken as the optimal user interface.

[0092] In some optional embodiments, after matching the optimal user interface, the process further includes:

[0093] (1) Collect feedback data of the current user within the second and first preset historical time periods;

[0094] (2) Based on the feedback data, adjust the UI element data in the optimal user interface, and use the adjusted user interface as the optimal user interface.

[0095] Based on the same inventive concept, embodiments of the present invention also provide an adaptive layout system for a user interface, the structure of which is as follows: Figure 4 As shown, it includes:

[0096] The data acquisition module 41 is used to acquire user behavior data of multiple users within a first preset historical time period, as well as device information of the devices used by each user and UI element data of the current system on the corresponding device.

[0097] The data processing and data analysis module 42 is used to obtain different types of first behavior patterns based on the user behavior data of each user and the device information of the devices used by each user; the first behavior pattern represents the user's operation preference for a single action.

[0098] The preference learning module 43 is used to process each first behavior pattern to obtain multiple second behavior patterns, which represent the user's operation preferences for continuous actions.

[0099] The layout optimization module 44 is used to draw multiple interface layouts based on multiple second behavior modes and the UI element data of the current system on the corresponding device; the interface layout represents the optimal layout on the device under the second behavior mode.

[0100] To more clearly explain the adaptive layout system for the user interface, refer to... Figure 5 As shown, Figure 5 This is a diagram of the adaptive layout system architecture for the user interface, where:

[0101] • UI element recognition module: Automatically identifies and classifies UI elements in the front-end page, and transmits the identified UI element information to the artificial intelligence algorithm analysis engine through the back-end server;

[0102] • User behavior collection module: Collects and analyzes user interaction data with the front-end user interface, and transmits the collected user behavior data to the artificial intelligence algorithm analysis engine through the back-end server;

[0103] • Device Characteristics Analyzer: Ensures the system can automatically detect and adapt to the type of device the user is using, adjusting the UI layout and elements accordingly.

[0104] • Backend server: Stores user behavior data, runs artificial intelligence algorithms, and processes real-time feedback from the frontend.

[0105] • Artificial intelligence algorithm analysis engine: Processes and analyzes user behavior data, including data preprocessing, data analysis, and user preference learning modules. It analyzes the identified UI element data and user behavior data, and uses the processed data to optimize the layout engine to dynamically adjust the UI layout; it also makes personalized recommendations based on user feedback and adjusts the UI to meet users' individual needs.

[0106] • Layout optimization engine: Adjusts the UI layout based on data analyzed by artificial intelligence algorithms and information provided by the UI element recognition module.

[0107] • Real-time feedback mechanism: Allows users to provide feedback directly on the interface, which is collected in real time and used to further optimize the UI design.

[0108] For example, on mobile devices, the system analyzes user swipes and clicks to identify the most frequently accessed functional areas. Based on this data, the layout optimization engine automatically adjusts the positions of buttons and links, moving them to more easily accessible areas of the screen, or reordering interface elements according to user frequency, thereby improving clickability and user satisfaction.

[0109] Furthermore, the system can intelligently adjust the interface layout based on user habits, such as one-handed or two-handed operation, ensuring easy operation regardless of how the user holds the device. For example, for one-handed operation, the system may group the main navigation buttons and controls towards the bottom or side of the screen for easy thumb access.

[0110] For example, on desktop devices, the system automatically adjusts the layout and font size based on the screen size and resolution to provide the best reading experience. For instance, for high-resolution displays, the system increases font size and element spacing to ensure readability, while optimizing the layout to make full use of screen space and provide richer information display. The system can also intelligently adapt to the user's work environment and habits, such as multi-monitor setups or specific application window layouts. For example, if a user typically uses two applications side-by-side, the system can automatically adjust the interfaces of these applications to provide a better visual and operational experience when they are side-by-side.

[0111] Regarding the adaptive layout system of the user interface in the above embodiments, the specific way in which each module performs operations has been described in detail in the embodiments related to the method, and will not be elaborated here.

[0112] Unless otherwise specifically stated, terms such as processing, calculation, operation, determination, display, etc., may refer to the actions and / or processes of one or more processing or computing systems or similar devices that represent the manipulation and conversion of data representing physical (e.g., electronic) quantities within the registers or memory of the processing system into other data similarly representing physical quantities within the memory, registers, or other such information storage, transmission, or display devices of the processing system. Information and signals can be represented using any of a variety of different techniques and methods. For example, data, instructions, commands, information, signals, bits, symbols, and chips mentioned throughout the above description can be represented by voltage, current, electromagnetic waves, magnetic fields or particles, light fields or particles, or any combination thereof.

[0113] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process may be rearranged without departing from the scope of this disclosure. The appended method claims provide elements of various steps in an exemplary order and are not intended to limit the scope to the specific order or hierarchy described.

[0114] In the detailed description above, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are explicitly stated in each claim. Rather, as reflected in the appended claims, the invention is presented with fewer features than all of the features in a single disclosed embodiment. Therefore, the appended claims are hereby explicitly incorporated into the detailed description, with each claim representing a separate preferred embodiment of the invention.

[0115] Those skilled in the art will also understand that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments herein can be implemented as electronic hardware, computer software, or a combination thereof. To clearly illustrate the interchangeability between hardware and software, the various illustrative components, blocks, modules, circuits, and steps described above are generally described in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. Those skilled in the art can implement the described functionality in alternative ways for each specific application; however, such implementation decisions should not be construed as departing from the scope of this disclosure.

[0116] The steps of the methods or algorithms described in conjunction with the embodiments herein can be directly embodied in hardware, software modules executed by a processor, or a combination thereof. The software modules can reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. The ASIC can reside in a user terminal. Alternatively, the processor and storage medium can exist as discrete components in the user terminal.

[0117] For software implementation, the techniques described in this application can be implemented using modules (e.g., procedures, functions, etc.) that perform the functions described in this application. This software code can be stored in memory units and executed by a processor. The memory units can be implemented within the processor or outside the processor; in the latter case, they are communicatively coupled to the processor via various means, as is well known in the art.

[0118] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that further combinations and arrangements of the various embodiments are possible. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term "comprising" as used in the specification or claims is interpreted in a manner similar to the term "including," as interpreted when used as a conjunction in the claims. Additionally, the use of any term "or" in the specification of the claims is intended to mean "non-exclusive or."

Claims

1. An adaptive layout method for a user interface, characterized in that, include: Obtain user behavior data of multiple users within a first preset historical time period, as well as device information of the devices used by each user and UI element data of the current system on the corresponding device; Based on the user behavior data of each user and the device information of the devices used by each user, different types of first behavior patterns are obtained; The first behavioral pattern represents the user's operational preferences for a single action; The various first behavior patterns are processed to obtain multiple second behavior patterns, and the second behavior patterns represent the user's operational preferences for continuous actions. Based on the multiple second behavior patterns and the UI element data of the current system on the corresponding device, multiple interface layouts are drawn and saved; the interface layout represents the optimal layout under the second behavior pattern on a device.

2. The method as described in claim 1, characterized in that, Based on the user behavior data of each user and the device information of each device, different types of first behavior patterns are obtained, including: Perform data cleaning and formatting on the user behavior data of each user; For each user's processed user behavior data and the device information of the device used by each user, a sequence analysis method is used to obtain the first behavior pattern corresponding to each user behavior data. The device information includes device type, screen size, and screen resolution. Classify the primary behavioral patterns; A clustering algorithm is used to obtain different types of first behavior models based on the classified first behavior patterns. Each type has multiple first behavior patterns.

3. The method as described in claim 2, characterized in that, The processing of various first behavior patterns yields multiple second behavior patterns, including: By employing recurrent neural networks and long short-term memory networks, the time-series characteristics of each first behavioral pattern under various categories are processed to obtain the second behavioral pattern corresponding to each category.

4. The method as described in claim 1, characterized in that, Based on the multiple second behavior patterns and the UI element data of the current system on the corresponding device, various interface layouts are drawn, including: For each of the second behavior modes, based on the second behavior mode and the device information in the second behavior mode, adjust the UI element data of the current system on the corresponding device in each second behavior mode, and draw the interface layout of each second behavior mode on different devices.

5. The method as described in claim 4, characterized in that, The method further includes: Collect feedback data from each user within the first preset historical time period; For each user, based on the user's feedback data, adjust the UI element data of the device used by the user.

6. A method for determining an optimal user interface, characterized in that, include: Get current device information and data of various UI elements within the current application; Collect current user behavior data within a first preset historical time period, and process the current user behavior data; Based on the processed current user behavior data, current device information, and UI element data, the optimal user interface is matched from a variety of saved interface layouts.

7. The method as described in claim 6, characterized in that, After matching the optimal user interface, it also includes: Collect feedback data from the current user within a second preset historical time period; Based on the feedback data, the UI element data in the optimal user interface is adjusted, and the adjusted user interface is taken as the optimal user interface.

8. An adaptive layout system for a user interface, characterized in that, include: The data acquisition module is used to acquire user behavior data of multiple users within a first preset historical time period, as well as device information of the devices used by each user and UI element data of the current system on the corresponding device. The data processing and data analysis module is used to obtain different types of first behavior patterns based on the user behavior data of each user and the device information of the devices used by each user. The first behavioral pattern represents the user's operational preferences for a single action; The preference learning module is used to process each of the first behavior patterns to obtain multiple second behavior patterns, whereby the second behavior patterns represent the user's operational preferences for continuous actions. The layout optimization module is used to draw various interface layouts based on the multiple second behavior patterns and the UI element data of the current system on the corresponding device. The interface layout represents an optimal layout on a device in the second behavior mode.

9. A computer storage medium, characterized in that, The computer storage medium stores computer-executable instructions, which, when executed by a processor, implement the adaptive layout method of the user interface as described in any one of claims 1-5 or the method for determining the optimal user interface as described in any one of claims 6-7.

10. A terminal device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the adaptive layout method of the user interface as described in any one of claims 1-5 or the method for determining the optimal user interface as described in any one of claims 6-7.

Images