Intelligent adaptive processing method and device for foldable equipment, equipment and medium

Abstract

The invention discloses an intelligent adaptive processing method and device for foldable equipment, the equipment and a medium. The method comprises the following steps: acquiring collected data of the foldable equipment; the collected data comprises a system environment, user behavior data, interface parameters and sensor data; configuring the pre-trained large language model to a foldable device based on a system environment; performing interactive training on a preset deep learning network based on the user behavior data, and deploying the trained deep learning network to a foldable device; constructing a page layout of the foldable equipment by utilizing a responsive design technology based on the interface parameters; adjusting a page layout based on the sensor data; and according to the page layout, performing adaptive adjustment on a target application running in a visual interface of the foldable equipment. The method can achieve the deep learning and prediction of the use habits and demands of the user, intelligently adjusts the function and interface layout of the user, and can be widely applied to the technical field of equipment adaptation.

Description

Technical Field

[0001] The present invention relates to the field of device adaptation technology, and in particular to an intelligent adaptation processing method, device, equipment and medium for a foldable device. Background Art

[0002] There are already some foldable adaptation technologies on the market, which mainly focus on basic adaptation solutions such as screen rotation and interface zooming. However, with the popularity of foldable devices and users' pursuit of intelligent experience, these traditional technologies have gradually shown their limitations. They can often only provide a single adaptation mode and lack in-depth consideration of user personalized needs and device status changes. Summary of the invention

[0003] The present invention proposes an intelligent adaptive processing method, device, equipment and medium for a foldable device, aiming to solve one of the technical problems in the related art at least to a certain extent. The embodiments of the present invention can intelligently realize adaptive processing of a foldable device.

[0004] On the one hand, an embodiment of the present invention provides an intelligent adaptive processing method for a foldable device, comprising:

[0005] Acquire collected data of the foldable device; the collected data includes system environment, user behavior data, interface parameters and sensor data;

[0006] Configure the pre-trained large language model to the foldable device based on the system environment;

[0007] Interactively train the preset deep learning network based on user behavior data, and deploy the trained deep learning network to foldable devices;

[0008] Use responsive design techniques to build page layouts for foldable devices based on interface parameters; adjust page layouts based on sensor data;

[0009] According to the page layout, the target application running in the visual interface of the foldable device is adapted and adjusted.

[0010] Optionally, configuring the pre-trained large language model to the foldable device based on the system environment includes the following steps:

[0011] Use a large-scale corpus to perform language modeling on the preset initial large language model to obtain the trained second largest language model;

[0012] Performing model adaptation processing on the second largest language model based on the system environment of the foldable device, and then configuring the obtained large language model to the foldable device;

[0013] Among them, the model adaptation process includes quantization operation and pruning operation.

[0014] Optionally, the collected data also includes usage data of the large language model; and the method further includes the following steps:

[0015] Continuously train and update large language models based on usage data.

[0016] Optionally, interactive training of a preset deep learning network based on user behavior data includes the following steps:

[0017] A neural network for sequence data processing is obtained as a deep learning network; the neural network is pre-configured based on application requirements of the foldable device;

[0018] Interactive training of deep learning networks based on user behavior data combined with sensor data.

[0019] Optionally, the method further comprises the following steps:

[0020] Based on the preset application scenarios, the deep learning network deployed on the foldable device is tested for scenario application to obtain test data;

[0021] Tune and iterate large language models based on test data.

[0022] Optionally, the interface parameters include a screen size range and a folding state; constructing a page layout of a foldable device using a responsive design technology based on the interface parameters; and adjusting the page layout based on sensor data, including the following steps:

[0023] According to the screen size range of the foldable device, use the flow layout and / or grid layout to build the page layout corresponding to each folding state of the foldable device;

[0024] The current target folding state of the foldable device is determined based on the sensor data, and the target page layout configuration corresponding to the target folding state is used as the page layout of the foldable device.

[0025] Optionally, adapting and adjusting the target application running in the visual interface of the foldable device according to the page layout includes the following steps:

[0026] Acquire adaptation data of the target application based on an application program interface of the target application;

[0027] According to the page layout of the foldable device, the layout adaptation data of the target application is matched from the adaptation data, and the target application running in the visual interface is adapted and adjusted based on the layout adaptation data.

[0028] On the other hand, an embodiment of the present invention provides an intelligent adaptive processing device for a foldable device, including:

[0029] The first module is used to obtain the collected data of the foldable device; the collected data includes system environment, user behavior data, interface parameters and sensor data;

[0030] The second module is used to configure the pre-trained large language model to the foldable device based on the system environment;

[0031] The third module is used to interactively train the preset deep learning network based on user behavior data, and deploy the trained deep learning network to the foldable device;

[0032] The fourth module is used to build the page layout of the foldable device based on the interface parameters using responsive design technology; adjust the page layout based on sensor data;

[0033] The fifth module is used to adapt and adjust the target application running in the visual interface of the foldable device according to the page layout.

[0034] Optionally, the second module is specifically used for:

[0035] Use a large-scale corpus to perform language modeling on the preset initial large language model to obtain the trained second largest language model;

[0036] Performing model adaptation processing on the second largest language model based on the system environment of the foldable device, and then configuring the obtained large language model to the foldable device;

[0037] Among them, the model adaptation process includes quantization operation and pruning operation.

[0038] Furthermore, the device also includes:

[0039] The sixth module is used to continuously train and update the large language model based on usage data.

[0040] Optionally, the third module is specifically used for:

[0041] A neural network for sequence data processing is obtained as a deep learning network; the neural network is pre-configured based on application requirements of the foldable device;

[0042] Interactive training of deep learning networks based on user behavior data combined with sensor data.

[0043] Furthermore, the device also includes:

[0044] The seventh module is used to perform scenario application testing on the deep learning network deployed on the foldable device based on a preset application scenario to obtain test data;

[0045] The eighth module is used to tune and iterate the large language model based on test data.

[0046] On the other hand, an embodiment of the present invention provides an electronic device, including: a processor and a memory; the memory is used to store programs; the processor executes the program to implement the above-mentioned intelligent adaptive processing method for the foldable device.

[0047] On the other hand, an embodiment of the present invention provides a computer storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor, it is used to implement the above-mentioned intelligent adaptive processing method of the foldable device.

[0048] The embodiment of the present invention obtains the collected data of the foldable device; the collected data includes the system environment, user behavior data, interface parameters and sensor data; based on the system environment, the pre-trained large language model is configured to the foldable device; based on the user behavior data, the preset deep learning network is interactively trained, and the trained deep learning network is deployed to the foldable device; based on the interface parameters, the page layout of the foldable device is constructed using responsive design technology; based on the sensor data, the page layout is adjusted; according to the page layout, the target application running in the visual interface of the foldable device is adapted and adjusted. The present invention relies on large language model technology and deep learning algorithms, and by constructing corresponding models, it can achieve deep learning and prediction of user usage habits and needs. At the same time, combined with responsive user interface design and device state perception based on sensor data, the device can intelligently adjust its functions and interface layout according to the specific needs and current state of the user, including the folded or unfolded state of the device. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0050] Figure 1 A schematic diagram of a flow chart of an intelligent adaptive processing method for a foldable device provided by an embodiment of the present invention;

[0051] Figure 2 A timing diagram of a business scenario of an example of the large language model technology provided by an embodiment of the present invention;

[0052] Figure 3 A flowchart of an example of implementing intelligent adaptation of FoldableDevice using a large language model provided by an embodiment of the present invention;

[0053] Figure 4 A timing diagram of a business scenario of an example of a deep learning algorithm technology provided by an embodiment of the present invention;

[0054] Figure 5 A flowchart of an example of deep learning algorithm training and tuning provided by an embodiment of the present invention;

[0055] Figure 6 A timing diagram of a business scenario of an example of a responsive user interface design technology provided by an embodiment of the present invention;

[0056] Figure 7 A timing diagram of a business scenario of a technical example of a device state perception and response system provided by an embodiment of the present invention;

[0057] Figure 8 A timing diagram of a business scenario of a foldable device technology example provided by an embodiment of the present invention;

[0058] Fig. 9 A schematic diagram of the process entity relationship for realizing the intelligent adaptation of FoldableDevice provided by an embodiment of the present invention;

[0059] Fig.10a A schematic diagram of a process for defining an adaptation strategy and configuration and using a responsive layout technology provided in an embodiment of the present invention;

[0060] Fig.10b A schematic diagram of a flow chart of a folding state change of a monitoring device and a dynamic layout adjustment according to an embodiment of the present invention;

[0061] Fig.10c A schematic diagram of the process of application state management and recovery, performance optimization and resource management provided by an embodiment of the present invention;

[0062] Fig.10d A schematic diagram of the process of multi-window and split-screen mode support and intelligent input and interaction optimization provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0064] It should be noted that, although the functional modules are divided in the system schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first / S100", "second / S200", etc. in the specification, claims and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0065] Reference to "embodiments" in the present invention means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in the present invention may be combined with other embodiments.

[0066] To facilitate the understanding of the technical solution of the present invention, the following is an explanation of the specific names of the technical features that may appear in the technical solution of the present invention:

[0067] Foldable Device: refers to electronic devices with foldable displays or other foldable components, such as foldable mobile phones, tablets, etc. Such devices can switch between folded and unfolded states, providing different usage modes and experiences.

[0068] Foldable Technology: refers to technology that allows electronic devices (such as mobile phones, tablets, etc.) to be physically folded or bent. This technology uses innovative designs such as flexible screens and special hinge mechanisms to enable the device to be folded into a more compact form when not in use, making it easier to carry and store, and to unfold into a larger screen area when needed, providing a better visual experience and usage functions.

[0069] Large Language Model (LLM): A natural language processing technology based on deep learning. Through large-scale text data pre-training, the model can understand and generate natural language text. Large language models can handle a variety of natural language tasks, such as text classification, question answering, and dialogue, and are an important path to artificial intelligence.

[0070] Deep Learning Algorithms: A machine learning algorithm based on artificial neural networks. Its core idea is to simulate the neural network of the human brain by building a multi-layer neural network structure, so as to achieve learning and feature extraction of complex data.

[0071] Adaptive processing: refers to the ability of a system or device to automatically adjust its configuration, parameters, or behavior based on the current environment, user behavior, or other conditions. In Foldable Devices, adaptive processing may involve adjusting the user interface, application layout, or functionality based on the folded state of the device.

[0072] User Interface (UI): refers to the interface through which users interact with devices or software, including visual elements (such as buttons, icons, text) and interaction methods (such as touch and click). In Foldable Device, the user interface needs to be adaptively adjusted according to the folding state of the device to ensure a good user experience.

[0073] The embodiment of the present invention provides an intelligent adaptive processing method for a foldable device, referring to Figure 1 , Figure 1 A flowchart of an intelligent adaptive processing method for a foldable device applied to a terminal according to an embodiment of the present invention. Figure 1 , the method comprises the following steps:

[0074] S100, obtaining collected data of the foldable device;

[0075] It should be noted that the collected data includes system environment, user behavior data, interface parameters and sensor data;

[0076] S200, configuring the pre-trained large language model to the foldable device based on the system environment;

[0077] It should be noted that, in some embodiments, configuring the pre-trained large language model to the foldable device based on the system environment may include the following steps: using a large-scale corpus to perform language modeling on the preset initial large language model to obtain a trained second large language model; performing model adaptation processing on the second large language model based on the system environment of the foldable device, and then configuring the obtained large language model to the foldable device; wherein the model adaptation processing includes quantization operations and pruning operations.

[0078] In some embodiments, the collected data also includes usage data of the large language model; the method may also include the following steps: continuously training and updating the large language model based on the usage data.

[0079] For example, in some specific implementations, a pre-trained large language model (LLM) is configured on a foldable device to improve the efficiency and experience of users in scenarios such as intelligent text input and automatic translation. Through a series of model selection and training, model adaptation and optimization, and model update and maintenance steps, the efficient operation and continuous optimization of the large language model on the foldable device are achieved. The technical solution can be specifically implemented as follows:

[0080] 1. Model selection and training:

[0081] Choose a suitable large language model architecture: Based on the characteristics of foldable devices and user needs, choose a large language model architecture such as Transformer that is efficient and has strong language understanding and generation capabilities. Considering the portability and performance limitations of foldable devices, the accuracy and computational efficiency of the model should be taken into account when selecting the model.

[0082] Pre-training with large-scale corpora: Collect and organize large-scale corpora covering multiple languages ​​and multiple fields. Improve the model's ability to understand and generate language through language modeling tasks, such as Masked Language Modeling (MLM). During the pre-training process, multilingual data can be introduced to enhance the model's cross-language understanding and translation capabilities.

[0083] Provide intelligent functions on foldable devices: Integrate the trained second largest language model into the input method, translation application and other scenarios of foldable devices. Provide intelligent text input suggestions, such as automatic completion, error correction, association, etc., to improve user input efficiency. Implement automatic translation function to support seamless communication between users in different language environments.

[0084] 2. Model adaptation and optimization:

[0085] Quantization operation: Convert the floating-point parameters in the model into low-precision integers or fixed-point numbers to reduce the model storage space and computational complexity. During the quantization process, it is necessary to balance the accuracy and performance of the model to ensure that the quantized model can still maintain high accuracy and operating efficiency on foldable devices.

[0086] Pruning: Remove unimportant weights or neurons in the model to reduce the complexity and computation of the model. During the pruning process, importance assessment methods (such as absolute value based on weights, gradient, etc.) can be used to determine which weights can be removed. After pruning, the model needs to be fine-tuned to restore the accuracy lost due to pruning.

[0087] Optimization for specific hardware and operating systems: Further optimize the model for the specific hardware (such as CPU, GPU, NPU, etc.) and operating system environment (such as Android, iOS, etc.) of foldable devices. Use hardware acceleration libraries (such as TensorFlow Lite, ONNX Runtime, etc.) and optimization tools provided by the operating system (such as AOT compilation, memory management, etc.) to improve the operating efficiency of the model.

[0088] 3. Model update and maintenance:

[0089] Regularly collect usage data: Collect data on users using large language models on foldable devices, including input text, model output, user feedback, etc. Usage data should be anonymized and desensitized to protect user privacy.

[0090] Continuously train and update models: Based on the collected usage data, continuously train the model to optimize the model's performance and adapt to user usage habits and changes in demand. During the training process, incremental learning, transfer learning and other methods can be used to improve training efficiency and the stability of model updates.

[0091] Implement version control: Record and manage each version of the model to ensure the stability and compatibility of model updates. When updating the model, sufficient testing should be performed to ensure that the new version of the model can run stably on foldable devices and has improved performance.

[0092] Through the above technical solutions and implementation steps, the pre-trained large language model can be efficiently and stably configured on foldable devices, providing users with intelligent, efficient and convenient text input and translation functions. At the same time, by continuously collecting usage data and optimizing the model, the performance of the model and user experience can be continuously improved.

[0093] S300, interactively training a preset deep learning network based on user behavior data, and deploying the trained deep learning network to a foldable device;

[0094] It should be noted that, in some embodiments, interactive training of a preset deep learning network based on user behavior data may include the following steps: obtaining a neural network for sequence data processing as a deep learning network; pre-configuring the neural network based on the application requirements of the foldable device; and interactively training the deep learning network based on the user behavior data combined with sensor data.

[0095] In some embodiments, the method may further include the following steps: performing scenario application testing on the deep learning network deployed on the foldable device based on a preset application scenario to obtain test data; and tuning and iterating the large language model based on the test data.

[0096] For example, in some specific implementations, applying deep learning algorithm technology to foldable devices can be implemented as follows:

[0097] 1. Selection and configuration of deep learning network:

[0098] Neural network selection: Choose a suitable neural network model based on the application requirements of the Foldable Device. For example, for image recognition, you can choose a convolutional neural network (CNN) for processing, because CNN performs well in processing image data and can extract features in images and classify them.

[0099] For sequence data processing tasks such as speech recognition and text generation, you can choose recurrent neural networks (RNNs) or their variants, such as long short-term memory networks (LSTMs) or gated recurrent units (GRUs). These networks can handle time dependencies in sequence data and are suitable for tasks such as speech recognition.

[0100] Pre-configuration of neural network: After selecting the neural network model, it needs to be pre-configured according to the hardware characteristics of the Foldable Device and application requirements. For example, adjust the network's number of layers, number of neurons, activation function and other parameters to optimize the model's performance and resource consumption.

[0101] Considering that Foldable Devices may have different folding forms and screen sizes, the neural network model also needs to adapt to different screen resolutions and interaction methods.

[0102] 2. Interactive training of deep learning networks:

[0103] Data acquisition and preprocessing: Acquire sensor data and user behavior data from the Foldable Device. Sensor data may include data from accelerometers, gyroscopes, cameras, etc. User behavior data includes user clicks, slides, folds, and other operation data. Preprocess the acquired data, including data cleaning, denoising, normalization, and other operations to improve data quality and training results.

[0104] Interactive training process: Combine sensor data and user behavior data to interactively train the deep learning network. During the training process, the network parameters and structure are adjusted to optimize the model performance to make it more suitable for the hardware characteristics and usage scenarios of the Foldable Device. During the training process, methods such as transfer learning can also be used to utilize existing model parameters and knowledge structures to accelerate the training process and improve the accuracy of the model.

[0105] 3. Scenario application testing and tuning of deep learning networks:

[0106] Scenario application testing: Deploy the trained deep learning network to the Foldable Device and conduct tests in actual scenarios. During the test, simulate the user's operations in different scenarios and collect test data. The test data includes indicators such as the model's recognition accuracy, response time, and resource consumption, which are used to evaluate the performance and stability of the model.

[0107] Tuning and iteration: Tune and iterate the deep learning network based on test data. Improve the accuracy and efficiency of the model by adjusting network parameters, optimizing model structure, and increasing training data. At the same time, the hardware limitations and user experience requirements of the Foldable Device must be considered to ensure that the model does not consume excessive device resources or affect user experience while maintaining high performance.

[0108] 4. Specific application scenario examples:

[0109] Image recognition: Implement image recognition functions on Foldable Device, such as identifying objects, scenes, or faces in photos taken by users. Through deep learning algorithms, the accuracy and speed of image recognition are improved to provide users with a better photo taking and browsing experience.

[0110] Speech recognition: Use deep learning algorithms to implement speech recognition functions, such as recognizing user voice commands, voice search, etc. By optimizing the model structure and parameters, the accuracy and robustness of speech recognition are improved, allowing users to interact with Foldable Device more conveniently.

[0111] Intelligent recommendation: Combine user behavior data and deep learning algorithms to achieve intelligent recommendation function. By analyzing user click, browse, purchase and other behavior data, it recommends content or products of interest to users. At the same time, it can also make personalized recommendations and displays based on the user's folding form and screen size.

[0112] In summary, the application of deep learning algorithm technology on Foldable Device can achieve a more intelligent, efficient and personalized user experience. At the same time, through continuous tuning and iteration, the accuracy and efficiency of the model can be further improved to meet the ever-changing needs of users.

[0113] S400, constructing a page layout for a foldable device using responsive design techniques based on interface parameters; adjusting the page layout based on sensor data;

[0114] It should be noted that the interface parameters include a screen size range and a folding state; in some embodiments, a page layout of a foldable device is constructed using responsive design technology based on the interface parameters; adjusting the page layout based on sensor data may include the following steps: according to the screen size range of the foldable device, a page layout corresponding to each folding state of the foldable device is constructed using a flow layout and / or a grid layout; based on the sensor data, the current target folding state of the foldable device is determined, and the target page layout configuration corresponding to the target folding state is used as the page layout of the foldable device.

[0115] For example, in some specific implementations, the page layout adaptation optimization can be implemented as follows:

[0116] 1. Interface layout design:

[0117] 1. Consideration of screen size range and folding state:

[0118] Fluid Layout: Fluid layout allows interface elements to dynamically adjust their size and position according to the screen size. For example, when the Foldable Device is unfolded, the page can display more content and a wider layout; when folded, the page layout automatically adjusts to fit the smaller screen, ensuring that important information remains visible and easy to operate.

[0119] Grid Layout: Grid layout divides the page into multiple grid units, each of which can accommodate different interface elements. By adjusting the number of columns and rows of the grid, it can adapt to different screen sizes and folding states. For example, in the expanded state, more columns can be used to display more complex information structures; in the folded state, the number of columns can be reduced to simplify the layout.

[0120] 2. Target folding state and page layout configuration:

[0121] Sensor data (such as accelerometers, gyroscopes, etc.) can be used to detect the current folding state of the Foldable Device. For example, when the device changes from an unfolded state to a folded state, the sensor sends a corresponding signal.

[0122] Based on the detected target folding state, the system can automatically switch to the corresponding target page layout configuration. This means that users can get an interface layout that matches the current device state without having to manually adjust settings.

[0123] 2. Interaction design optimization:

[0124] 1. Optimization of touch and gesture recognition:

[0125] On Foldable Devices, touch and gesture recognition are the main interaction methods. Therefore, these interaction methods need to be optimized to improve the usability and responsiveness of the user interface.

[0126] For example, you can design some specific gestures to quickly access common functions or switch page layouts. At the same time, you need to ensure that these gestures can be accurately recognized and executed on different screen sizes and folding states.

[0127] 2. Instant feedback mechanism:

[0128] To improve the user experience, you need to design an immediate feedback mechanism to inform users whether their operation is successful. For example, when a button on the screen is touched, a short animation or sound effect can be displayed to confirm that the operation has been received.

[0129] When folding or unfolding the device, visual or auditory feedback can also be provided to inform the user of the change in device status.

[0130] 3. Performance optimization and testing:

[0131] 1. Performance optimization:

[0132] Performance optimization of responsive user interfaces is crucial to ensure a smooth user experience. Performance can be improved by reducing page load time, optimizing the rendering process, and more.

[0133] For example, you can use lazy loading technology to delay the loading of non-critical resources (such as pictures and videos) to reduce the initial loading time of the page. At the same time, you can use hardware acceleration technology to improve rendering speed and fluency.

[0134] 2. Compatibility test:

[0135] Since Foldable Devices come in a variety of models and configurations, it is necessary to ensure that the responsive user interface provides a consistent and stable user experience on a variety of devices.

[0136] The compatibility and stability of the interface can be verified by testing on Foldable Devices of different models and configurations. These tests should include tests on different screen sizes, resolutions, processor performance, etc.

[0137] Examples of actual application scenarios:

[0138] Suppose a foldable device is developing an e-book reading application for a new Foldable Device. In this application, we can use the above responsive design techniques and optimization methods to ensure that users can get a good reading experience in different device states.

[0139] When the device is expanded, the app can use flow layout and grid layout to display wider pages and more book covers. Users can browse different books or chapters by sliding the screen.

[0140] When the device is folded, the app automatically adjusts its layout to fit the smaller screen. For example, some non-critical interface elements (such as sidebars or bottom navigation bars) can be hidden and the main content area can be centered. At the same time, touch and gesture recognition can be optimized to ensure that users can easily turn pages or adjust reading settings.

[0141] Through the application of these embodiments and technical solutions, a more flexible, easy-to-use and efficient user interface experience can be provided for users of Foldable Devices.

[0142] S500: Adapt and adjust a target application running in a visual interface of the foldable device according to a page layout.

[0143] It should be noted that, in some embodiments, adapting and adjusting the target application running in the visual interface of the foldable device according to the page layout may include the following steps: obtaining adaptation data of the target application based on the application program interface of the target application; matching and obtaining layout adaptation data of the target application from the adaptation data according to the page layout of the foldable device, and adapting and adjusting the target application running in the visual interface based on the layout adaptation data.

[0144] For example, in some specific implementations, the adaptation optimization for the application and the corresponding hardware integration can be implemented as follows:

[0145] 1. Detailed process of operating system and software adaptation:

[0146] 1.1 Development and use of application programming interface (API):

[0147] API development: In order to support the folding and unfolding state switching of the screen of foldable devices, the operating system needs to develop a series of specific APIs. These APIs can detect the current screen state of the device (such as folded, half-folded, fully unfolded, etc.) and provide corresponding screen parameters (such as screen size, resolution, orientation, etc.).

[0148] Software adaptation: Developers can use these APIs to adapt the target application. For example, when the application detects that the device is in a folded state, it can automatically adjust the interface layout to adapt to the smaller screen size; when the device is unfolded, it can display more content or provide a richer interactive experience.

[0149] 1.2 Acquisition and matching of adaptation data:

[0150] Preparation of adaptation data: During the development of the target application, developers will prepare corresponding adaptation data in advance according to different screen layouts and sizes. These adaptation data may include layout files, resource files (such as pictures, fonts, etc.) and corresponding logic processing codes.

[0151] Matching of adaptation data: When a foldable device changes its page layout (such as switching from a folded state to an unfolded state), the operating system calls the corresponding API and passes the current screen status information. The target application can obtain the current screen status by monitoring these API calls and match the corresponding layout adaptation data from the pre-prepared adaptation data.

[0152] Execution of adaptation adjustment: Based on the matched layout adaptation data, the target application automatically adjusts the layout, resources, and logic processing in its visual interface to adapt to the current screen layout and size.

[0153] 2. Detailed process of hardware integration and testing:

[0154] 2.1 Integration of hardware components:

[0155] Integration of flexible screens: The flexible screen is one of the core components of foldable devices. During the integration process, it is necessary to ensure that the screen can be folded and unfolded smoothly while maintaining good display and touch performance.

[0156] Integration of sensors and processors: Sensors are used to detect information such as the folding state and screen orientation of the device, while the processor is responsible for processing this information and controlling the operation of the device. During the integration process, it is necessary to ensure that the connection between these hardware components is stable and reliable and can work together.

[0157] 2.2 Testing and Verification:

[0158] Folding and unfolding state testing: During the folding and unfolding process of the device, multiple tests are required to ensure that hardware components such as the screen, sensor, and processor can work stably. At the same time, key indicators such as the display effect, touch performance, and battery life of the device in different states also need to be tested.

[0159] Verification of user experience: After hardware integration and testing are completed, user experience verification is required. This includes testing the user's ease of operation, comfort, and overall satisfaction when the device is folded and unfolded. By collecting user feedback and suggestions, the design and functions of the device can be further improved and optimized.

[0160] 3. Expansion of application scenarios:

[0161] Office scenario: In office scenarios, users can use foldable devices to display more documents or spreadsheets to improve work efficiency. When the device needs to be carried, it can be folded into a smaller size for easy carrying.

[0162] Entertainment scenarios: In entertainment scenarios, users can use foldable devices to watch videos or play games. When the device is unfolded, a larger screen area and better visual effects can be obtained; when the device is folded, it can be easily put into a pocket or bag.

[0163] Learning scenarios: In learning scenarios, students can use foldable devices to read e-books, take notes, or conduct online learning. The folding and unfolding functions of the device can help students better adapt to different learning environments and needs.

[0164] In summary, by combining the specific implementation methods of operating system and software adaptation as well as hardware integration and testing, foldable device technology can provide users with a richer and more diverse experience. At the same time, by adapting and adjusting the target application, it can ensure that it can maintain good performance under different screen layouts and sizes.

[0165] In order to explain the principle of the technical solution of the present invention in detail, the overall process of the present invention is described below in combination with some specific embodiments. It is easy to understand that the following is an explanation of the technical principle of the present invention and cannot be regarded as a limitation of the present invention.

[0166] First of all, it should be noted that with the rapid development of science and technology, people's demand for smart devices is also constantly changing. The emergence of Foldable Device has brought new opportunities and challenges to the market. Traditional adaptation technology can no longer meet users' pursuit of efficient, convenient and personalized user experience. Against this background, the solution of the present invention came into being. It combines the latest deep learning algorithms and responsive user interface design to bring users an unprecedented intelligent experience. The present invention has introduced this new folding adaptation solution, which aims to provide users with a more intelligent and personalized user experience through deep learning algorithms and responsive user interface design. The technical solution of the present invention can be implemented as follows:

[0167] 1. Large Language Model Intelligent Adaptation (LLM):

[0168] ① Model selection and training: Select a large language model architecture suitable for Foldable Device, such as Transformer, and perform pre-training. Use large-scale corpora for language modeling tasks to improve the model's ability to understand and generate language. Provide intelligent text input suggestions, automatic translation and other functions on Foldable Device to improve user input efficiency and experience;

[0169] ② Model adaptation and optimization: Adapt and optimize the model for the specific hardware and operating system environment of Foldable Device, such as quantization and pruning, to reduce the model size and improve operating efficiency. Ensure that large language models can run efficiently on Foldable Device without taking up too much storage space and computing resources;

[0170] ③ Model update and maintenance: Regularly collect usage data of Foldable Device users for continuous training and updating of the model. Implement version control to ensure the stability and compatibility of model updates. Through continuous learning and optimization, make the large language model more adaptable to the usage habits and demand changes of Foldable Device users, such as Figure 2 and Figure 3 As shown, Figure 2 This is a sequence diagram of a business scenario for a large language model technology example. Figure 3 Flowchart for implementing the FoldableDevice intelligent adaptation example using a large language model (LLM).

[0171] 2. Deep Learning Algorithms Technology:

[0172] ① Algorithm selection and implementation: According to the application requirements of Foldable Device, select appropriate deep learning algorithms, such as convolutional neural network (CNN) for image processing and recurrent neural network (RNN) for sequence data processing. Implement intelligent functions such as image recognition and speech recognition on Foldable Device to improve the device's interactive capabilities and user experience;

[0173] ② Algorithm training and tuning: Use sensor data and user behavior data on Foldable Device to train deep learning algorithms. Optimize model performance by adjusting algorithm parameters and structure. Make deep learning algorithms more adaptable to the hardware characteristics and usage scenarios of Foldable Device, and improve the accuracy and efficiency of the algorithms.

[0174] ③Algorithm deployment and testing: Deploy the trained deep learning algorithm to the Foldable Device and conduct tests in actual scenarios. Collect test data for further tuning and iteration of the algorithm. Ensure that the deep learning algorithm can run stably on the Foldable Device and meet actual application requirements, such as Figure 4 and Figure 5 As shown, Figure 4 A timing diagram of a business scenario for a deep learning algorithm technology example. Figure 5Flowchart of an example of training and tuning a deep learning algorithm.

[0175] 3. Responsive UI Design Technology:

[0176] ① Interface layout design: Design an adaptive interface layout according to the screen size and folding state of the Foldable Device. Use responsive design techniques such as flow layout and grid layout to ensure the adaptability of interface elements under different screen sizes and resolutions. Provide a consistent and optimized user interface experience regardless of whether the Foldable Device is in the expanded or folded state;

[0177] ②Interaction design optimization: Optimize the interaction design of the user interface for the specific interaction methods of Foldable Device (such as touch, gesture recognition, etc.). Ensure that users can operate conveniently and get instant feedback. Improve the user interaction experience of Foldable Device, allowing users to complete various tasks more efficiently;

[0178] ③Performance optimization and testing: Optimize the performance of the responsive user interface, such as reducing page loading time, optimizing the rendering process, etc. Test on Foldable Devices of different models and configurations to ensure the compatibility and stability of the interface. Ensure that the responsive user interface can provide a smooth and stable user experience on various Foldable Devices, such as Figure 6 The following is a sequence diagram of a business scenario for an example of responsive user interface design technology.

[0179] 4.Device State Sensing and Response System Technology:

[0180] ① Sensor data collection and processing: Use various sensors on the Foldable Device (such as accelerometers, gyroscopes, etc.) to collect device status data. Preprocess and extract features of the data for subsequent analysis and decision-making. Monitor the usage status and environmental changes of the Foldable Device in real time to provide data support for intelligent adaptive processing;

[0181] ② State identification and response strategy formulation: Based on the collected sensor data, use machine learning algorithms to identify the current state of the device (such as unfolded, folded, handheld, etc.). According to the state identification results, formulate corresponding response strategies and adjust the user interface or functions. Enable the Foldable Device to automatically adjust its functions and interface layout according to the user's usage status and scenario, providing a more personalized user experience;

[0182] ③ System optimization and feedback mechanism: Optimize the device status perception and response system to improve the accuracy of status recognition and response speed. Establish a user feedback mechanism to collect user satisfaction and suggestions on system response for continuous improvement and optimization of the system. Ensure that the device status perception and response system can work stably and accurately, and continuously optimize according to user feedback to improve user experience, such as Figure 7 The following is a timing diagram of a business scenario of an example of the device status perception and response system technology.

[0183] 5. Foldable Technology:

[0184] ① Operating system and software adaptation: Adapt and optimize the operating system for the foldable device's screen folding features. Develop an application programming interface (API) that supports the switching of screen folding and unfolding states to facilitate developers to adapt and develop software. Ensure that the operating system and software of the Foldable Device can fully utilize the screen folding features to provide a richer and more diverse user experience.

[0185] ② Hardware integration and testing: Integrate flexible screens, sensors, processors and other hardware components into FoldableDevice and conduct rigorous testing and verification. Ensure that the device can work stably in both folded and unfolded states and meet user needs. Provide high-quality Foldable Device products to meet users' high expectations and diverse needs for foldable devices, such as Figure 8 Shown is a timing diagram of a business scenario of a foldable device technology example.

[0186] Furthermore, in some specific embodiments, adaptive processing and compatible processing for Foldable Device, such as Fig. 9 As shown, the following is a specific technical implementation step:

[0187] 1. Define the adaptation strategy and configuration: Based on the characteristics of the Foldable Device, such as the screen size range and hinge position, the application's adaptation strategy and configuration are defined. The Large Language Model (LLM) is used for language understanding and generation to provide intelligent text processing functions for the application. At the same time, the user behavior is analyzed through the Deep Learning Algorithms Technology to predict the user's usage habits in different folding states, thereby optimizing the layout and interaction design of the application;

[0188] 2. Use responsive layout technology: Utilize CSS media queries and responsive layout frameworks such as Bootstrap, Flexbox, Grid Layout, etc. to design layouts that can adapt to different screen sizes and directions. By defining breakpoints, different style rules are applied under different screen sizes to ensure the continuity and aesthetics of the layout. At the same time, combined with responsive UI design technology, intelligent adaptation and layout adjustment of interface elements are achieved;

[0189] 3. Monitor the folding state changes of the device: By calling the built-in sensor interface of the device, such as the hinge sensor API, or monitoring the system broadcast, such as Intent, the folding state change information of the device can be obtained in real time. The device state sensing and response system technology (Device State Sensing and Response System Technology) can be used to achieve accurate perception and rapid response to the folding state;

[0190] 4. Implement dynamic layout adjustment: In the callback function or event handler, dynamically adjust the layout of the application according to the new folding state information. Use dynamic layout adjustment technology, such as dynamically adding or deleting views, adjusting layout parameters, etc., and combine deep learning algorithm technology to learn user operation habits and interface usage, further optimize layout adjustment strategies, and ensure that the application can maintain a good user experience in different folding states;

[0191] 5. Application state management and recovery: Use local storage technologies such as SharedPreferences and LocalStorage to save and restore state information such as reading progress and user settings during the application life cycle. Use a large language model to understand and store user input and settings to achieve intelligent state management and recovery;

[0192] 6. Performance optimization and resource management: In view of the large screen and high resolution characteristics of Foldable Device, lazy loading technology is used to reduce the initial loading time; asynchronous processing is used to avoid blocking the main thread; multimedia resources such as pictures and videos are compressed and optimized. At the same time, the hardware acceleration capabilities of the device are reasonably used to improve rendering performance; resource usage is predicted and optimized through deep learning algorithms to further improve application performance;

[0193] 7. Multi-window and split-screen mode support: Using the multi-window or split-screen mode API provided by the operating system, applications can be run simultaneously in different windows or split-screens. Through the cross-window data sharing mechanism, data consistency between applications in different windows or split-screens is ensured. At the same time, window management and operation interfaces are provided to facilitate users to switch windows, resize and close windows. Combined with responsive user interface design technology, the interface layout and interaction of applications in multi-window and split-screen modes are ensured to remain optimized and consistent;

[0194] 8. Intelligent input and interaction optimization: Using large language models and deep learning algorithm technology, intelligent text input prediction and error correction functions are realized, which improves the user input experience on Foldable Device. At the same time, the user's interactive behavior is learned and analyzed, and the application's interactive logic and response speed are optimized through deep learning algorithms;

[0195] 9. Cross-platform compatibility implementation: In the process of realizing the cross-platform compatibility of Foldable Device, the Foldable Technology standards and specifications were adopted to design a unified adaptive processing framework, and the interface standards of core functions such as device status monitoring, layout adjustment and resource management were clarified. Subsequently, standardized interfaces were implemented through interface-oriented programming to adapt to the differences between different operating systems. The development of the platform adaptation layer ensures the seamless integration of the framework on multiple platforms, including mainstream systems such as Android and iOS. After comprehensive testing and verification, the stable operation and adaptive adjustment of the application on different platforms are achieved. In addition, through continuous iteration and optimization, the timeliness of the technical solution and the continuous improvement of user experience are ensured.

[0196] The above steps can fully realize adaptive processing and compatible processing on Foldable Device. Using a series of advanced technologies such as large language models, deep learning algorithm technology, responsive user interface design technology, device state perception and response system technology, no matter how the user folds or unfolds the device, the application can automatically adjust the layout, optimize performance, and provide intelligent input and interactive experience. The above process is detailed in the following. Fig.10a , Fig.10b , Fig.10c and Fig.10d .

[0197] The solution of the present invention relies on the large language model technology (LLM) and deep learning algorithms (Deep Learning Algorithms), and realizes deep learning and prediction of user usage habits and needs by building a multi-layer neural network model. At the same time, combined with responsive user interface design (Responsive UI Design), device state sensing and response system (Device State Sensing and Response System) and Foldable Technology, the device can intelligently adjust its functions and interface layout according to the user's specific needs and current status, including the folded or unfolded state of the device. These exclusive and unique background technology points provide strong technical support and unique competitive advantages for our solution.

[0198] In summary, the introduction of the solution of the present invention is an inevitable choice based on market demand and technological progress. It relies on exclusive and unique background technology points to bring users a more intelligent and personalized use experience. Compared with the general solutions on the market, this solution has significant advantages and competitiveness. With the continuous development of technology and the further expansion of the market, the solution of the present invention will play an important role in the field of Foldable Device and bring users an unprecedented intelligent experience.

[0199] The present invention aims to realize intelligent adaptive processing of Foldable Device in various usage scenarios by comprehensively utilizing large language model (LLM), deep learning algorithm technology (Deep Learning Algorithms Technology), responsive user interface design technology (Responsive UI Design Technology), device state sensing and response system technology (Device State Sensing and Response System Technology) and foldable device technology (Foldable Technology). Specifically, the method and device can use LLM and deep learning algorithm technology to deeply learn and predict the user's operating habits and needs, and then dynamically adjust the interface layout and function display through responsive user interface design technology to adapt to different usage scenarios. At the same time, with the help of device state sensing and response system technology, the method and device can sense the folding or unfolding state of Foldable Device in real time, and make corresponding intelligent adjustments accordingly to ensure the consistency and convenience of user experience.

[0200] Compared with the common solutions on the market, the advantage of the invention lies in its high degree of intelligence and personalization. Traditional FoldableDevice adaptation solutions often adopt fixed interface layouts and function settings. This method lacks dynamic consideration of the actual needs of users and cannot flexibly adapt to the usage habits of different users. The invention makes full use of the large language model (LLM) and deep learning algorithm technology, and realizes personalized interface layout and function adjustment through deep learning and prediction of user operating habits and needs. This intelligent processing method can automatically optimize the interface layout and function settings according to the user's usage habits and scenario requirements, thereby greatly improving the user experience. In addition, the invention also incorporates the device state perception and response system technology, which can perceive the folding or unfolding state of the FoldableDevice in real time, and make intelligent responses accordingly, further enhancing the practicality and convenience of the device, and bringing users a more intelligent and efficient use experience.

[0201] The creativity of the present invention lies in its organic integration of multiple advanced technologies to form a new, intelligent FoldableDevice adaptive processing method and device. This innovation not only improves the user experience of FoldableDevice, but also brings revolutionary changes to the further development of the device field. Through the application of the present invention, FoldableDevice will adapt to various usage scenarios more intelligently and conveniently, bringing users an unprecedented usage experience. At the same time, the launch of the present invention will also promote the further development and innovation of related technologies in the device field.

[0202] Compared with the prior art, the present invention has at least the following beneficial effects:

[0203] 1. By real-time monitoring of the state of FoldableDevice and using the Device State Sensing and Response System Technology, the present invention can ensure the accuracy and timeliness of adaptive processing. This function provides users with a more stable and reliable user experience, and also provides application developers with rich device state data, making it easier for them to use Deep Learning Algorithms Technology to develop applications that better meet user needs;

[0204] 2. The dynamic layout adjustment function of the present invention, combined with the responsive UI design technology (Responsive UI Design Technology), can automatically adjust the layout of the application interface according to the real-time status of the Foldable Device. This ensures that users can obtain a good visual experience and convenient application operation in different usage scenarios. This function effectively improves user satisfaction and also enhances the adaptability and market competitiveness of the application;

[0205] 3. Through intelligent analysis of the state changes and application requirements of FoldableDevice and the use of deep learning algorithms, the present invention can dynamically adjust the allocation of system resources to ensure that applications can run smoothly in different states. This function effectively improves the overall performance and battery life of the device, bringing users a more durable and efficient user experience;

[0206] 4. In order to adapt to the special form of FoldableDevice, the present invention specially designs a user interaction adaptation function. This function optimizes the interaction modes such as touch feedback, gesture recognition and voice control, and improves the accuracy and naturalness of voice control by combining the large language model (LLM), providing a more natural and convenient user operation experience. It enhances the interactivity and immersion between the user and the device, allowing the user to complete tasks more happily and efficiently during use;

[0207] 5. The cross-platform compatibility function of the present invention achieves seamless compatibility and adaptive processing on multiple operating systems and platforms by building a unified adaptive processing framework and standardized interface design, and closely integrating the standards and specifications of Foldable Technology. This innovative design not only simplifies the development process and significantly reduces the complexity and cost of cross-platform application development, but also improves the versatility and market share of applications, opening up broader market prospects and business opportunities for application developers. In addition, it also provides users with more flexible and diverse application choices, ensuring a consistent and smooth user experience across different operating systems and devices, enhancing user satisfaction and loyalty, and further consolidating the market competitiveness of the product;

[0208] 6. Through a highly abstract and modular architecture, the adaptive logic is effectively decoupled from the underlying operating system, which improves the flexibility and scalability of the system architecture and enables the adaptive strategy to quickly respond to iterative updates of Foldable Device technology. The intelligent decision-making engine embedded in the framework continuously optimizes the adaptive strategy by continuously learning the usage patterns and behavioral data of Foldable Device to ensure that the system always maintains the best performance. This intelligent adaptive framework design allows developers to focus on the innovation and optimization of application functions without worrying about underlying adaptation issues, thereby improving overall development efficiency and product quality. In addition, the unified adaptive processing framework and standardized interface design reduce the complexity of cross-platform adaptation, accelerate the popularization of Foldable Device applications, and further promote the progress and development of the entire industry.

[0209] On the other hand, an embodiment of the present invention provides an intelligent adaptive processing device for a foldable device, which may include:

[0210] The first module is used to obtain the collected data of the foldable device; the collected data includes system environment, user behavior data, interface parameters and sensor data;

[0211] The second module is used to configure the pre-trained large language model to the foldable device based on the system environment;

[0212] The third module is used to interactively train the preset deep learning network based on user behavior data, and deploy the trained deep learning network to the foldable device;

[0213] The fourth module is used to build the page layout of the foldable device based on the interface parameters using responsive design technology; adjust the page layout based on sensor data;

[0214] The fifth module is used to adapt and adjust the target application running in the visual interface of the foldable device according to the page layout.

[0215] In some embodiments, the second module may be specifically used for:

[0216] Use a large-scale corpus to perform language modeling on the preset initial large language model to obtain the trained second largest language model;

[0217] Performing model adaptation processing on the second largest language model based on the system environment of the foldable device, and then configuring the obtained large language model to the foldable device;

[0218] Among them, the model adaptation process includes quantization operation and pruning operation.

[0219] Furthermore, the device may also include:

[0220] The sixth module is used to continuously train and update the large language model based on usage data.

[0221] In some embodiments, the third module may be specifically used for:

[0222] A neural network for sequence data processing is obtained as a deep learning network; the neural network is pre-configured based on application requirements of the foldable device;

[0223] Interactive training of deep learning networks based on user behavior data combined with sensor data.

[0224] Furthermore, the device may also include:

[0225] The seventh module is used to perform scenario application testing on the deep learning network deployed on the foldable device based on a preset application scenario to obtain test data;

[0226] The eighth module is used to tune and iterate the large language model based on test data.

[0227] The contents of the method embodiments of the present invention are all applicable to the device embodiments. The functions specifically implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0228] On the other hand, an embodiment of the present invention further provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above sensitive information method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0229] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0230] Another aspect of an embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the above method.

[0231] It should be noted that the computer-readable medium shown in the embodiment of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (Compact Disc Read to Only Memory, CD to ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0232] The contents of the method embodiments of the present invention are all applicable to the computer-readable storage medium embodiments. The functions specifically implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0233] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0234] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0235] It should be noted that, although several modules of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0236] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD to ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation of the present invention.

[0237] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operation and logic flow presented by the present invention. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part described as a larger operation is performed independently.

[0238] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of various functional modules in the device disclosed in the present invention, the actual implementation of the module will be understood within the conventional skills of engineers. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0239] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0240] The logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be embodied in any computer-readable medium for use by an instruction execution device, apparatus or device (such as a computer-based device, a device including a processor, or other device that can fetch instructions from an instruction execution device, apparatus or device and execute the instructions), or in conjunction with such instruction execution device, apparatus or device. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution device, apparatus or device, or in conjunction with such instruction execution device, apparatus or device.

[0241] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0242] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0243] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0244] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0245] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. An intelligent adaptive processing method for a foldable device, characterized in that: The following steps are involved: Acquire collected data of the foldable device; the collected data includes system environment, user behavior data, interface parameters and sensor data; configuring a pre-trained large language model to the foldable device based on the system environment; Interactively training a preset deep learning network based on the user behavior data, and deploying the trained deep learning network to the foldable device; Building a page layout of the foldable device using responsive design technology based on the interface parameters; adjusting the page layout based on the sensor data; According to the page layout, the target application running in the visual interface of the foldable device is adapted and adjusted.

2. The intelligent adaptive processing method for a foldable device according to claim 1, characterized in that: The configuring the pre-trained large language model to the foldable device based on the system environment comprises the following steps: Use a large-scale corpus to perform language modeling on the preset initial large language model to obtain the trained second largest language model; performing model adaptation processing on the second large language model based on the system environment of the foldable device, and then configuring the obtained large language model to the foldable device; The model adaptation process includes quantization operation and pruning operation.

3. The intelligent adaptive processing method for a foldable device according to claim 2, characterized in that: The collected data also includes usage data of the large language model; the method also includes the following steps: The large language model is continuously trained and updated based on the usage data.

4. The intelligent adaptive processing method for a foldable device according to claim 1, characterized in that: The interactive training of a preset deep learning network based on the user behavior data comprises the following steps: Acquire a neural network for sequence data processing as the deep learning network; the neural network is pre-configured based on the application requirements of the foldable device; The deep learning network is interactively trained based on the user behavior data in combination with the sensor data.

5. The intelligent adaptive processing method for a foldable device according to claim 4, characterized in that: The method further comprises the following steps: Performing a scenario application test on the deep learning network deployed on the foldable device based on a preset application scenario to obtain test data; The large language model is tuned and iterated based on the test data.

6. The intelligent adaptive processing method for a foldable device according to claim 1, characterized in that: The interface parameters include a screen size range and a folding state; and the page layout of the foldable device is constructed using responsive design technology based on the interface parameters; Adjusting the page layout based on the sensor data comprises the following steps: According to the screen size range of the foldable device, constructing a page layout corresponding to each folded state of the foldable device by using a flow layout and / or a grid layout; A current target folding state of the foldable device is determined based on the sensor data, and a target page layout configuration corresponding to the target folding state is used as the page layout of the foldable device.

7. The intelligent adaptive processing method for a foldable device according to claim 1, characterized in that: The step of adapting and adjusting the target application running in the visual interface of the foldable device according to the page layout comprises the following steps: Acquiring adaptation data of the target application based on an application program interface of the target application; According to the page layout of the foldable device, the layout adaptation data of the target application is matched and obtained from the adaptation data, and the target application running in the visual interface is adapted and adjusted based on the layout adaptation data.

8. An intelligent adaptive processing device for a foldable device, characterized in that: include: The first module is used to obtain the collected data of the foldable device; The collected data includes system environment, user behavior data, interface parameters and sensor data; A second module is used to configure the pre-trained large language model to the foldable device based on the system environment; A third module is used to interactively train a preset deep learning network based on the user behavior data, and deploy the trained deep learning network to the foldable device; A fourth module is used to construct a page layout of the foldable device using a responsive design technology based on the interface parameters; adjusting the page layout based on the sensor data; The fifth module is used to adapt and adjust the target application running in the visual interface of the foldable device according to the page layout.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 7.

10. A computer storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the method according to any one of claims 1 to 7 when executed by the processor.

Images