Self-adaptive user interface dynamic rendering method and device, equipment, medium and product

Abstract

The invention provides an adaptive user interface dynamic rendering method and device, equipment, a medium and a product, and relates to the technical field of interactive design, and the method comprises the following steps: obtaining source data aiming at a current user interface on a browser; symbolizing the user interaction data to obtain symbolized interaction data, and converting the natural language information into an original feature vector; performing interface change prediction according to the original feature vector to obtain a prediction vector; verifying the prediction vector according to the symbolized interaction data; a large model layer in a preset neural symbol renderer is adopted, interface change information is generated according to the prediction vector, and the interface change information at least comprises an interface change rule set; and according to the interface adjustment rule set, performing interface rendering by adopting a preset rendering engine to obtain an updated user interface. According to the method, the intelligence, transparency and credibility of self-adaptive adjustment of the user interface are improved.

Description

Technical Field

[0001] This application relates to the field of interaction design technology, and more specifically, to an adaptive user interface dynamic rendering method, apparatus, device, medium, and product. Background Technology

[0002] With the increasing complexity of internet applications and the continuous improvement of users' personalized needs, front-end user interfaces are rapidly developing towards intelligence, dynamism, and adaptability. In highly interactive scenarios, users expect the interface to understand their behavioral intentions, contextual environment, and even natural language commands in real time, and automatically adjust the layout, function presentation, and interaction logic accordingly.

[0003] Currently, web interface development mainly relies on a technical system that combines structured markup languages, style control languages, and scripting languages, along with modern front-end frameworks, and uses mechanisms such as modular design and virtual document object models to build and refresh the interface.

[0004] However, existing technologies mainly rely on purely data-driven models for behavior prediction or directly call external language processing services to generate responses, resulting in a lack of transparency in the entire decision-making process, an inability to provide clear logical basis, and a black box effect. Summary of the Invention

[0005] The purpose of this application is to address the shortcomings of the prior art by providing an adaptive user interface dynamic rendering method, apparatus, device, medium, and product to improve the intelligence, transparency, and reliability of adaptive user interface adjustments.

[0006] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: In a first aspect, one embodiment of this application provides an adaptive user interface dynamic rendering method, the method comprising: Obtain source data for the current user interface on the browser, the source data including: user interaction data and natural language information; The user interaction data is symbolized using the browser's local preset user context model to obtain symbolic interaction data, and the natural language information is converted into raw feature vectors. Using a neural network layer in a preset neural symbol renderer, interface change prediction is performed based on the original feature vector to obtain a prediction vector, which is used to characterize the user interface change intention. The predicted vector is verified using the symbolic layer in the preset neural symbolic renderer based on the symbolic interaction data. If the predicted vector passes the verification, the large model layer in the preset neural symbol renderer is used to generate interface change information based on the predicted vector. The interface change information includes at least: an interface change rule set. Based on the interface adjustment rule set, the interface is rendered using a preset rendering engine to obtain the updated user interface.

[0007] Optionally, the source data further includes: device context data; the method further includes: Using the user context model, the device context data is symbolized to obtain symbolized device data; The step of using the symbolic layer in the preset neural symbolic renderer to verify the predicted vector based on the symbolic interaction data includes: The predicted vector is verified using the symbolic layer in the preset neural symbolic renderer, based on the symbolic interaction data and the symbolic device data.

[0008] Optionally, the interface change information further includes: natural language description information corresponding to the interface change rule set; Before rendering the interface using a preset rendering engine based on the interface change rule set to obtain the updated user interface, the method further includes: The interface change simulation is performed according to the interface change rule set to obtain interface change simulation information, which includes: simulated natural language information. Perform a consistency check on the natural language description information and the simulated natural language information; The step of rendering the interface using a preset rendering engine based on the interface change rule set to obtain the updated user interface includes: If the consistency check passes, the interface is rendered using the preset rendering engine according to the interface change rule set to obtain the updated user interface.

[0009] Optionally, the method further includes: If the consistency check fails, an interface optimization instruction is generated based on the natural language description information and the simulated natural language information. Based on the interface optimization instructions, generate prompt words; Based on the prompt words, the interface change rule set is adjusted using the large model layer in the preset neural symbol renderer to obtain the adjusted interface rule set. The step of rendering the interface using a preset rendering engine based on the interface change rule set to obtain the updated user interface includes: Based on the adjusted interface rule set, the interface is rendered using the preset rendering engine to obtain the updated user interface.

[0010] Optionally, the interface change simulation information further includes: simulated interface performance parameters; the method further includes: The performance parameters of the simulated interface are verified. If the consistency check passes, the interface is rendered using the preset rendering engine according to the interface change rule set to obtain the updated user interface, including: If the consistency check passes and the performance check passes, then the interface is rendered using the preset rendering engine according to the interface change rule set to obtain the updated user interface.

[0011] Optionally, the user interaction data includes: mouse trajectory and keyboard input; the device context data includes: screen resolution and battery level.

[0012] Secondly, another embodiment of this application provides an adaptive user interface dynamic rendering apparatus, the apparatus comprising: The acquisition module is used to acquire source data for the current user interface on the browser, the source data including: user interaction data and natural language information; The conversion module is used to symbolize the user interaction data using the browser's local preset user context model, obtain symbolic interaction data, and convert the natural language information into the original feature vector; The prediction module is used to predict interface changes based on the original feature vector using a neural network layer in a preset neural symbol renderer, and to obtain a prediction vector, which is used to characterize the user interface change intention. The verification module is used to verify the predicted vector based on the symbolic interaction data using the symbolic layer in the preset neural symbolic renderer. The generation module is used to generate interface change information based on the predicted vector, using the large model layer in the preset neural symbol renderer, if the predicted vector passes the verification. The interface change information includes at least: an interface change rule set. The rendering module is used to adjust the rule set according to the interface and use a preset rendering engine to render the interface to obtain the updated user interface.

[0013] Thirdly, another embodiment of this application provides a computer device, including: a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the adaptive user interface dynamic rendering method as described in any of the first aspects above.

[0014] Fourthly, another embodiment of this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the adaptive user interface dynamic rendering method described in any of the first aspects above.

[0015] Fifthly, another embodiment of this application provides a computer program product, the computer program product including computer program code, wherein when the computer program code is executed by a computing device, the computing device performs the steps of any of the adaptive user interface dynamic rendering methods described in the first aspect above.

[0016] The beneficial effects of this application are: This application provides an adaptive user interface dynamic rendering method, apparatus, device, medium, and product. By integrating a user context model and a neural symbol renderer locally in the browser, it achieves real-time perception and fusion processing of user interaction data and natural language information. It organically combines the predictive ability of the neural layer, the logical interpretability of the symbol layer, and the language understanding and generation capabilities of the large model into the front-end rendering process. It uses neural networks to accurately predict the intention of interface changes from user behavior feature vectors, and verifies the safety and rationality of the prediction results through symbol rules to avoid the risk of misoperation caused by black box decision-making. Furthermore, it generates a set of interface change rules containing natural language interpretations through the large model, which improves the intelligence, transparency, and credibility of the adaptive adjustment of the user interface, and ensures high performance, low latency, and privacy protection in the adaptive user interface dynamic rendering. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating an adaptive user interface dynamic rendering method provided in an embodiment of this application; Figure 2A flowchart illustrating the process of verifying predicted vectors in an adaptive user interface dynamic rendering method provided in this application; Figure 3 A flowchart illustrating the process of determining the updated user interface in an adaptive user interface dynamic rendering method provided in this application embodiment; Figure 4 A flowchart illustrating the process of determining the updated user interface in another adaptive user interface dynamic rendering method provided in this application embodiment; Figure 5 A flowchart illustrating the process of determining the updated user interface in another adaptive user interface dynamic rendering method provided in this application embodiment; Figure 6 A schematic diagram of the structure of an adaptive user interface dynamic rendering device provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the accompanying drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0020] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0021] It should be noted that the term "comprising" will be used in the embodiments of this application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0022] To clearly describe the method provided in the embodiments of this application, the method will be described below in conjunction with several accompanying drawings. Figure 1 A flowchart illustrating an adaptive user interface dynamic rendering method provided in this application embodiment is shown below. Figure 1 As shown, the method includes: Step 101: Obtain source data for the current user interface on the browser.

[0023] The source data consists of data collected from the current user interface on the browser. This source data includes user interaction data and natural language information. User interaction data refers to the interaction data between the user and the current interface on the browser, such as mouse clicks, scrolling paths, and touch gestures. Natural language information refers to the query statements entered by the user via voice or text boxes.

[0024] Optionally, user interaction data and natural language information can be obtained by capturing data from the current user interface on the browser.

[0025] Step 102: Using the browser's local preset user context model, symbolize the user interaction data to obtain symbolized interaction data, and convert the natural language information into the original feature vector.

[0026] The User Context Model (UCM) runs locally in the browser and is used to transform source data into a structured, processable data format. Symbolic interaction data is the result of abstracting user interaction behavior into high-level semantic symbols. For example, user interaction data can be mapped using a pre-defined mapping table to obtain corresponding symbolic interaction data, or user interaction data can be encrypted using a pre-defined symbol algorithm to obtain corresponding symbolic data. The original feature vector is the numerical vector corresponding to the natural language information.

[0027] Optionally, the browser's local preset user context model uses a preset mapping table to map user interaction data, thereby symbolizing the user interaction data and obtaining symbolized interaction data. The browser's local preset user context model's feature conversion module encodes natural language information and converts natural language information into raw feature vectors.

[0028] Step 103: Using the neural network layer in the preset neural symbol renderer, perform interface change prediction based on the original feature vector to obtain the prediction vector.

[0029] The pre-defined Neuro-Symbolic Renderer (NSR) includes neural layers, symbol layers, and a large model layer. The neural layers are used to predict intent using a convolutional neural network model, generating prediction vectors that represent the intent behind user interface changes. These neural layers are pre-trained using multiple raw feature vectors and their corresponding prediction vectors.

[0030] Optionally, a neural network layer in a pre-defined neural symbol renderer is used to predict interface changes based on the original feature vector, resulting in a prediction vector. The prediction vector represents the user interface change intent and the corresponding intent probability distribution, with the sum of multiple intent probabilities equal to 1.

[0031] Step 104: Using the symbolic layer in the preset neural symbolic renderer, the predicted vector is verified based on the symbolic interaction data.

[0032] The symbolic layer uses a logic inference engine to verify whether the intent prediction output by the neural layer conforms to the preset business logic. The inference engine in the symbolic layer includes multiple preset rules, and the prediction rules differ for different symbolic interaction data.

[0033] Optionally, a symbolic layer in a preset neural symbolic renderer is used to determine the preset rule corresponding to the symbolic data from multiple preset rules based on the symbolic interaction data, and the predicted vector of the preset rule corresponding to the symbolic data is verified. The verification result is either pass or fail.

[0034] Step 105: If the prediction vector is verified, use the large model layer in the preset neural symbol renderer to generate interface change information based on the prediction vector.

[0035] The large model layer is used to generate a set of dynamic interface change rules with natural language descriptions. The interface change information includes at least the interface change rule set, which is in the form of a symbol tree structure.

[0036] Optionally, if the predicted vector passes the verification, the large model layer in the preset neural symbol renderer is used to generate interface change information based on the predicted vector.

[0037] Step 106: Based on the interface adjustment rule set, use the preset rendering engine to render the interface and obtain the updated user interface.

[0038] The interface adjustment rule set describes how the current user interface should be adjusted, such as "expand details panel", "hide ad banner", "increase font size", etc.

[0039] Optionally, based on the interface adjustment rule set, the corresponding page rendering code is generated using a large model, and the interface is rendered using a preset rendering engine based on the page rendering code to obtain the updated user interface.

[0040] In this embodiment, by integrating a user context model and a neural symbol renderer locally in the browser, real-time perception and fusion processing of user interaction data and natural language information are achieved. The predictive ability of the neural layer, the logical interpretability of the symbol layer, and the language understanding and generation capabilities of the large model are organically combined in the front-end rendering process. The neural network accurately predicts the intention of interface changes from user behavior feature vectors, and the prediction results are verified for security and rationality through symbol rules to avoid the risk of misoperation caused by black box decision-making. Furthermore, the large model generates a set of interface change rules containing natural language interpretations, which improves the intelligence, transparency, and credibility of the adaptive adjustment of the user interface, and ensures high performance, low latency, and privacy protection in the dynamic rendering of the adaptive user interface.

[0041] Based on the above embodiments, the source data also includes: device context data; this application also provides a process for verifying predicted vectors in an adaptive user interface dynamic rendering method. Figure 2 A flowchart illustrating the verification process of predicted vectors in an adaptive user interface dynamic rendering method provided in this application is shown below. Figure 2 As shown, based on steps 101-106 above, the method further includes: Step 201: Using the user context model, symbolize the device context data to obtain symbolized device data.

[0042] Symbolized device data refers to data obtained by symbolizing device context data. Symbolization involves transforming raw data to obtain corresponding symbols or tags. Device context data refers to browser data during interaction with the browser. Device context data may include data corresponding to the browser's hardware devices, such as computing unit data, memory data, storage data, graphics system data, and audio system data. It may also include operating system data, software application data, network layer data, etc. This application embodiment does not impose any limitations on this.

[0043] Optionally, a user context model is employed to determine the various data types within the device context data. These data types are then symbolized based on corresponding symbolization rules, resulting in symbolized device data. If the device context data is numeric, a threshold is used to determine the corresponding symbol; if the device context data is text, regular expression matching is used for formatting.

[0044] In step 103 above, the symbolic layer in the preset neural symbolic renderer is used to verify the predicted vector based on the symbolic interaction data, including: Step 202: Using the symbolic layer in the preset neural symbolic renderer, the predicted vector is verified based on the symbolic interaction data and symbolic device data.

[0045] Optionally, based on the symbolic interaction data, symbolic device data, and prediction vector, an inference engine in the symbolic layer is used. The inference engine takes the prediction vector as the target and infers the rationality of the prediction vector based on the symbolic interaction data and symbolic device data. If a conflict rule is triggered, the prediction vector is determined to be invalid or needs to be adjusted. If no conflict rule is triggered, the prediction vector is determined to be valid.

[0046] For example, if symbolic interaction data indicates "the user is scrolling down frequently," "the dwell time is long," and "the user has not yet clicked the interaction button," and symbolic device data includes "the device is a mobile phone," "the current battery power is extremely low," and "the network connection speed is slow," then the rule engine's rule indicates "when the user's device battery is very low, unnecessary interface redraws and content loading should be minimized to save power and resource consumption." The predicted intent vector indicates "the user is likely to want to view more comments." Based on the symbolic interaction data, symbolic device data, predicted vector, and rule, it can be determined that the validation fails.

[0047] In this embodiment, a user context model is used to symbolize device context data. The symbolic layer in a neural symbolic renderer combines symbolic interaction data with device data to verify the predicted vector. This transforms the original, continuous device state into semantically discrete symbols, improving data interpretability and processing efficiency. Symbolic rules are used to logically verify the prediction results generated by the neural network, avoiding unreasonable rendering behavior caused by model misjudgment or environmental incompatibility. This reduces resource waste caused by invalid re-rendering and enhances user privacy and security while ensuring user experience.

[0048] Based on the above embodiments, the interface change information further includes: natural language description information corresponding to the interface change rule set; this application also provides a process for determining the updated user interface in an adaptive user interface dynamic rendering method. Figure 3 This is a flowchart illustrating the process of determining the updated user interface in an adaptive user interface dynamic rendering method provided in an embodiment of this application, as shown below. Figure 3 As shown, before rendering the interface using a preset rendering engine according to the interface change rule set in step 106 above to obtain the updated user interface, the method further includes: Step 301: Simulate interface changes based on the interface change rule set to obtain interface change simulation information.

[0049] The interface change simulation information includes: simulated natural language information. Interface change simulation involves the system building a lightweight virtual environment locally in the browser before actual rendering to pre-simulate the effects of user interface changes based on a set of interface change rules. For example, a lightweight virtual environment can be built based on WebAssembly or DOM snapshots. The simulated natural language information is automatically generated by the large model as a natural language description of the interface changes to be performed, such as: "The system has detected that you are comparing prices and has placed the product discount information at the top to express the intent and reason for the interface change simulation."

[0050] Optionally, a lightweight virtual environment is created, and interface changes are simulated within the lightweight virtual environment based on specific operation instructions and triggering conditions to obtain interface change simulation information.

[0051] Step 302: Perform a consistency check on the natural language description information and the simulated natural language information.

[0052] Among them, the natural language description information is text generated by the large model based on the interface change rule set, which is used to interpret the page changes in natural language.

[0053] Optionally, natural language description information and simulated natural language information are used to perform semantic analysis using a large model inference engine guided by pre-defined semantic matching or rules. Figure 1 Consistency analysis is performed to determine whether the page change information in the natural language description information is consistent with the simulated interface change information in the simulated natural language information, thereby verifying the consistency between the natural language description information and the simulated natural language information.

[0054] In step 106 above, the interface is rendered using a preset rendering engine based on the interface change rule set to obtain the updated user interface, including: Step 303: If the consistency check passes, render the interface using the preset rendering engine according to the interface change rule set to obtain the updated user interface.

[0055] Optionally, if the consistency check passes, it means that the natural language description information and the simulated natural language information are semantically consistent. Then, according to the interface change rule set, the interface is rendered using a preset rendering engine to obtain the updated user interface.

[0056] In this embodiment, by introducing a rule-based simulation and natural language consistency verification mechanism before interface rendering, the security and interpretability of adaptive user interface adjustments are improved. Actual rendering is only triggered after the verification passes. This prevents unreasonable interface changes caused by rule misuse, contextual bias, or component conflicts, achieving more reliable, transparent, and user-friendly dynamic interface updates.

[0057] Based on the above embodiments, this application also provides another process for determining the updated user interface in an adaptive user interface dynamic rendering method. Figure 4 A flowchart illustrating the process of determining the updated user interface in another adaptive user interface dynamic rendering method provided in this application embodiment is shown below. Figure 4 As shown, based on steps 301-303 above, the method further includes: Step 401: If the consistency check fails, generate interface optimization instructions based on the natural language description information and the simulated natural language information.

[0058] If the consistency check fails, it indicates that there is a semantic inconsistency between the original "natural language description information" and the simulated "simulated natural language information" generated after simulation, indicating that the interface changes deviate from the preset value, resulting in a fault or problem.

[0059] Optionally, if the consistency check fails, the discrepancies are determined based on the natural language description information and the simulated natural language information, and interface optimization instructions are generated based on these discrepancies. These interface optimization instructions provide suggestions for improvement. For example, an interface optimization instruction could be something like, "Please adjust the rule set to avoid triggering multiple pop-ups in form filling scenarios; inline hints or collapsible help should be prioritized to keep the interface simple."

[0060] Step 402: Generate prompt words according to the interface optimization instructions.

[0061] The prompts are used to guide the large model in generating the adjusted interface rule set.

[0062] Optionally, prompt words are generated based on interface optimization instructions, symbolic interaction data, symbolic device data, and prediction vectors.

[0063] Step 403: Based on the prompt words, use the large model layer in the preset neural symbol renderer to adjust the interface change rule set to obtain the adjusted interface rule set.

[0064] Optionally, based on the prompt words, the large model layer in the preset neural symbol renderer is used to adjust or add supplementary rules to the rules in the interface change rule set that may cause interface abnormalities, so as to obtain the adjusted interface rule set.

[0065] In step 106 above, the interface is rendered using a preset rendering engine based on the interface change rule set to obtain the updated user interface, including: Step 404: Render the interface using the preset rendering engine according to the adjusted interface rule set to obtain the updated user interface.

[0066] In this embodiment, by analyzing the difference between the original intent and the simulation results, optimization instructions are automatically generated and prompt words are constructed. This drives the large model layer in the neural symbol renderer to intelligently correct the rule set, effectively identifying and correcting unreasonable interface changes caused by context misjudgment or rule conflicts. This avoids the problem of relying on manual intervention in traditional systems and improves the robustness, interpretability, and consistency of user experience of the adaptive user interface.

[0067] Based on the above embodiments, the interface change simulation information further includes: simulated interface performance parameters; this application also provides a process for determining the updated user interface in another adaptive user interface dynamic rendering method. Figure 5 A flowchart illustrating the process of determining the updated user interface in another adaptive user interface dynamic rendering method provided in this application embodiment is shown below. Figure 5 As shown, based on steps 301-303 above, the method further includes: Step 501: Verify the performance parameters of the simulated interface.

[0068] The performance parameters may include: rendering frequency, first draw time, component loading latency, peak memory usage, CPU utilization, GPU utilization, and animation smoothness score.

[0069] Optionally, the rendering frequency, first-draw time, component loading delay time, peak memory usage, CPU utilization, GPU utilization, and animation smoothness score are compared with the corresponding rendering frequency threshold, first-draw time threshold, component loading delay time threshold, peak memory usage threshold, CPU utilization threshold, GPU utilization threshold, and animation smoothness score threshold, thereby enabling performance verification of the simulated interface performance parameters.

[0070] If the consistency check passes in step 401 above, the interface is rendered using a preset rendering engine according to the interface change rule set to obtain the updated user interface, including: Step 502: If the consistency check and performance check pass, then the interface is rendered using the preset rendering engine according to the interface change rule set to obtain the updated user interface.

[0071] If the performance verification passes, it means that the rendering frequency, first-draw time, component loading latency, peak memory usage, CPU utilization, GPU utilization, and animation smoothness score are all less than the corresponding thresholds. In this case, the preset rendering engine is used to render the interface according to the interface change rule set, resulting in the updated user interface. If the performance verification fails, it means that the browser's rendering effect is poor. In this case, the preset rendering engine is not used for interface rendering, and corresponding prompt information is displayed to the user.

[0072] In this embodiment, the dual pre-check mechanism of performance verification and consistency verification effectively ensures that the target interface meets the performance standards and data consistency requirements before rendering, avoiding the decline in user experience caused by interface lag, resource overload or state disorder, realizing the security, stability and intelligent control of interface updates, improving the overall system response efficiency and rendering success rate, and enhancing the robustness and maintainability of the human-computer interaction system.

[0073] Based on the same inventive concept, this application also provides an adaptive user interface dynamic rendering device corresponding to the adaptive user interface dynamic rendering method. Since the principle of the device in this application is similar to the adaptive user interface dynamic rendering method described above in this application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0074] Figure 6 This is a schematic diagram of the structure of an adaptive user interface dynamic rendering device provided in an embodiment of this application, as shown below. Figure 6 As shown, the device includes: The acquisition module 601 is used to acquire source data for the current user interface on the browser. The source data includes user interaction data and natural language information. The conversion module 602 is used to symbolize user interaction data using the browser's local preset user context model, obtain symbolized interaction data, and convert natural language information into raw feature vectors. The prediction module 603 is used to use the neural network layer in the preset neural symbol renderer to predict interface changes based on the original feature vector, and obtain a prediction vector. The prediction vector is used to represent the user interface change intention. The verification module 604 is used to verify the predicted vector based on the symbolic interaction data using the symbolic layer in the preset neural symbolic renderer. The generation module 605 is used to generate interface change information based on the predicted vector by using a large model layer in a preset neural symbol renderer if the prediction vector is verified. The interface change information includes at least: an interface change rule set. Rendering module 606 is used to adjust the rule set according to the interface and use a preset rendering engine to render the interface to obtain the updated user interface.

[0075] In one possible implementation, the source data further includes: device context data; the conversion module 602 is also used to: use a user context model to symbolize the device context data to obtain symbolized device data; the conversion module 602 is specifically used to: use the symbol layer in a preset neural symbol renderer to verify the prediction vector based on the symbolized interaction data and the symbolized device data.

[0076] In one possible implementation, the interface change information further includes: natural language description information corresponding to the interface change rule set; the rendering module 606 is also used to: simulate interface changes according to the interface change rule set to obtain interface change simulation information, the interface change simulation information including: simulated natural language information. Perform consistency checks on natural language description information and simulated natural language information; Rendering module 606 is specifically used for: if the consistency check passes, rendering the interface using a preset rendering engine according to the interface change rule set to obtain the updated user interface.

[0077] In one possible implementation, the rendering module 606 is further configured to: generate interface optimization instructions based on natural language description information and simulated natural language information if the consistency check fails; Based on the interface optimization instructions, generate prompt words; Based on the prompt words, the large model layer in the preset neural symbol renderer is used to adjust the interface change rule set to obtain the adjusted interface rule set. Rendering module 606 is specifically used to: render the interface using a preset rendering engine based on the adjusted interface rule set, and obtain the updated user interface.

[0078] In one possible implementation, the interface change simulation information further includes: simulated interface performance parameters; the rendering module 606 is also used to: perform performance verification on the simulated interface performance parameters. The rendering module 606 is specifically used to: if the consistency check and performance check pass, then render the interface using a preset rendering engine according to the interface change rule set to obtain the updated user interface.

[0079] In one possible implementation, user interaction data includes mouse movements and keyboard input; device context data includes screen resolution and battery level.

[0080] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0081] This application also provides a computer device. Figure 7 This application provides a schematic diagram of the structure of a computer device, as shown in the embodiment of the present application. Figure 7 As shown, the computer device includes a processor 701 and a memory 702, and optionally, a bus 703. The memory 702 stores machine-readable instructions executable by the processor 701. When the computer device is running, the processor 701 and the memory 702 communicate via the bus 703. When the machine-readable instructions are executed by the processor 701, the steps of the aforementioned adaptive user interface dynamic rendering method are performed.

[0082] This application also provides a computer-readable storage medium storing a computer program, which, when run by a processor, executes the steps of the above-described adaptive user interface dynamic rendering method.

[0083] This application also provides a computer program product, which includes computer program code. When the computer program code is executed by a computing device, the computing device performs the steps of the above-described adaptive user interface dynamic rendering method.

[0084] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems and devices described above can be referred to the corresponding processes in the method embodiments, and will not be repeated here. In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces; the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0085] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0086] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. An adaptive user interface dynamic rendering method, characterized in that, The method includes: Obtain source data for the current user interface on the browser, the source data including: user interaction data and natural language information; The user interaction data is symbolized using the browser's local preset user context model to obtain symbolized interaction data, and the natural language information is converted into the original feature vector. Using a neural network layer in a preset neural symbol renderer, interface change prediction is performed based on the original feature vector to obtain a prediction vector, which is used to characterize the user interface change intention. The predicted vector is verified using the symbolic layer in the preset neural symbolic renderer based on the symbolic interaction data. If the predicted vector passes the verification, the large model layer in the preset neural symbol renderer is used to generate interface change information based on the predicted vector. The interface change information includes at least: an interface change rule set. Based on the interface adjustment rule set, the interface is rendered using a preset rendering engine to obtain the updated user interface.

2. The method according to claim 1, characterized in that, The source data further includes: device context data; the method further includes: Using the user context model, the device context data is symbolized to obtain symbolized device data; The step of using the symbolic layer in the preset neural symbolic renderer to verify the predicted vector based on the symbolic interaction data includes: The predicted vector is verified using the symbolic layer in the preset neural symbolic renderer, based on the symbolic interaction data and the symbolic device data.

3. The method according to claim 1, characterized in that, The interface change information also includes: natural language description information corresponding to the interface change rule set; Before rendering the interface using a preset rendering engine based on the interface change rule set to obtain the updated user interface, the method further includes: The interface change simulation is performed according to the interface change rule set to obtain interface change simulation information, which includes: simulated natural language information. Perform a consistency check on the natural language description information and the simulated natural language information; The step of rendering the interface using a preset rendering engine based on the interface change rule set to obtain the updated user interface includes: If the consistency check passes, the interface is rendered using the preset rendering engine according to the interface change rule set to obtain the updated user interface.

4. The method according to claim 3, characterized in that, The method further includes: If the consistency check fails, an interface optimization instruction is generated based on the natural language description information and the simulated natural language information. Based on the interface optimization instructions, generate prompt words; Based on the prompt words, the interface change rule set is adjusted using the large model layer in the preset neural symbol renderer to obtain the adjusted interface rule set. The step of rendering the interface using a preset rendering engine based on the interface change rule set to obtain the updated user interface includes: Based on the adjusted interface rule set, the interface is rendered using the preset rendering engine to obtain the updated user interface.

5. The method according to claim 3, characterized in that, The interface change simulation information also includes: simulated interface performance parameters; the method further includes: The performance parameters of the simulated interface are verified. If the consistency check passes, the interface is rendered using the preset rendering engine according to the interface change rule set to obtain the updated user interface, including: If the consistency check passes and the performance check passes, then the interface is rendered using the preset rendering engine according to the interface change rule set to obtain the updated user interface.

6. The method according to claim 2, characterized in that, The user interaction data includes mouse movements and keyboard input; the device context data includes screen resolution and battery level.

7. An adaptive user interface dynamic rendering device, characterized in that, The device includes: The acquisition module is used to acquire source data for the current user interface on the browser, the source data including: user interaction data and natural language information; The conversion module is used to symbolize the user interaction data using the browser's local preset user context model, obtain symbolic interaction data, and convert the natural language information into the original feature vector; The prediction module is used to predict interface changes based on the original feature vector using a neural network layer in a preset neural symbol renderer, and to obtain a prediction vector, which is used to characterize the user interface change intention. The verification module is used to verify the predicted vector based on the symbolic interaction data using the symbolic layer in the preset neural symbolic renderer. The generation module is used to generate interface change information based on the prediction vector by using the large model layer in the preset neural symbol renderer if the prediction vector passes the verification. The interface change information includes at least: an interface change rule set. The rendering module is used to adjust the rule set according to the interface and use a preset rendering engine to render the interface to obtain the updated user interface.

8. A computer device, characterized in that, include: A processor and a memory, the memory storing machine-readable instructions executable by the processor, which, when the computer device is running, are executed by the processor to perform the steps of the adaptive user interface dynamic rendering method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the adaptive user interface dynamic rendering method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes computer program code, which, when executed by a computing device, performs the steps of the adaptive user interface dynamic rendering method according to any one of claims 1 to 6.

Images