Interface display method, device and storage medium

Abstract

The application discloses an interface display method, device and storage medium. The interface display method of the application embodiment comprises the following steps: determining a current cognitive load state of a user according to interaction behavior data of the user on an operation interface, judging whether the current cognitive load state of the user meets a visual optimization condition, if it is determined that the visual optimization condition is met, identifying a target area in the operation interface according to the interaction behavior data and / or an element type of an interface element in the operation interface, and performing visual noise reduction processing on the interface element in the target area according to an element noise reduction strategy corresponding to the current cognitive load state of the user.

Description

Technical Field

[0001] This application relates to the field of communications, and more particularly to an interface display method, device, and storage medium. Background Technology

[0002] With the rapid development of random computer technology and the widespread use of terminal devices, the number of information elements displayed on the terminal's interface when users access various business services has increased dramatically. This information overload phenomenon can easily cause visual fatigue and distraction for users during human-computer interaction, thereby reducing user operating efficiency and interactive experience.

[0003] In existing technologies, some solutions attempt to detect users' biometric data using external biosensor devices (such as eye trackers and heart rate sensors) to determine if the user is in a state of cognitive overload. Once a state of cognitive overload is identified, the system reduces the number of operations on the user interface. However, due to the high configuration cost of external biosensor devices, and the potential for reducing operations to disrupt the interface's display, the system can negatively impact user behavior and business processing efficiency. Therefore, there is a need to provide an interface display method that can quickly and accurately optimize visual noise during operation, thereby reducing user cognitive load and improving the efficiency of business service operations and user experience. Summary of the Invention

[0004] This application provides an interface display method, device, and storage medium to quickly and accurately optimize visual noise during operation, thereby reducing user cognitive load and improving user efficiency and user experience in handling business services.

[0005] In a first aspect, a method for displaying an interface is provided. The method includes: determining the user's current cognitive load state based on user interaction behavior data on the interface, and determining whether the user's current cognitive load state meets visual optimization conditions; if the visual optimization conditions are met, identifying a target area in the interface based on the interaction behavior data and / or the element type of the interface elements in the interface; and performing visual noise reduction processing on the interface elements in the target area according to an element noise reduction strategy corresponding to the user's current cognitive load state, wherein the visual noise reduction processing includes changing the visual presentation parameters of the interface elements to reduce the visual interference of the target area on the user.

[0006] Secondly, an interface display device is provided, the device comprising: a state recognition module, configured to determine the user's current cognitive load state based on user interaction behavior data on the operation interface, and to determine whether the user's current cognitive load state meets visual optimization conditions; a region recognition module, configured to, if determined to meet visual optimization conditions, identify a target region in the operation interface based on the interaction behavior data and / or the element type of the interface elements in the operation interface; and a visual noise reduction module, configured to perform visual noise reduction processing on the interface elements in the target region according to an element noise reduction strategy corresponding to the user's current cognitive load state, wherein the visual noise reduction processing includes changing the visual presentation parameters of the interface elements to reduce the visual interference of the target region on the user.

[0007] Thirdly, an interface display device is provided, the device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the interface display method as described in the first aspect.

[0008] Fourthly, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the interface display method as described in the first aspect.

[0009] Fifthly, a computer program product is provided, characterized in that it includes a computer program that, when executed by a processor, implements the steps of the interface display method as described in the first aspect.

[0010] The embodiments of this application adopt the following technical solutions: Based on the user's interactive behavior data on the operation interface, the user's current cognitive load state is determined, and it is judged whether the user's current cognitive load state meets the visual optimization conditions. If it is determined that the visual optimization conditions are met, the target area in the operation interface is identified based on the interactive behavior data and / or the element type of the interface elements in the operation interface. According to the element noise reduction strategy corresponding to the user's current cognitive load state, the interface elements in the target area are subjected to visual noise reduction processing. The visual noise reduction processing includes changing the visual presentation parameters of the interface elements to reduce the visual interference of the target area on the user.

[0011] The above-described technical solutions adopted in the embodiments of this application can achieve the following beneficial effects: First, based on user interaction data on the user interface, the user's current cognitive load state can be quickly and accurately determined. This avoids the high equipment configuration costs associated with relying on external biosensor devices to determine cognitive overload. In other words, it improves the efficiency and accuracy of cognitive load state identification while saving on configuration costs. Second, based on the element denoising strategy corresponding to the cognitive load state, visual denoising processing is performed on the target area identified based on interaction data and / or element type. This optimizes visual noise during user operations without altering the interface element structure, ensuring that the denoising intent aligns with the user's current operational intent. This reduces the user's cognitive load while improving the efficiency of business service operations and the user experience. Attached Figure Description

[0012] Figure 1 This is a schematic flowchart of an interface display method according to an embodiment of this application; Figure 2 This is a schematic diagram of the system architecture of an interface display system according to an embodiment of this application; Figure 3 This is a schematic flowchart of a method for determining cognitive load state according to an embodiment of this application; Figure 4 This is a schematic flowchart illustrating a method for determining whether visual optimization conditions are met according to an embodiment of this application; Figure 5 This is a schematic flowchart illustrating the process of determining an element noise reduction strategy according to an embodiment of this application; Figure 6 This is a schematic flowchart of a visual noise reduction process according to an embodiment of this application; Figure 7 This is a schematic diagram of the processing procedure of an interface display system according to an embodiment of this application; Figure 8 This is a schematic diagram of the operation page of a terminal device according to an embodiment of this application; Figure 9 This is a schematic diagram illustrating the area division of an operation page according to an embodiment of this application; Figure 10 This is a schematic diagram of the area division of the operation page according to another embodiment of this application; Figure 11 This is a schematic diagram illustrating the area division of a server operation page according to an embodiment of this application; Figure 12 This is a schematic flowchart of a visual fine-tuning process according to an embodiment of this application; Figure 13 This is a schematic flowchart illustrating the process of determining a target region according to an embodiment of this application; Figure 14 This is a schematic diagram of the structure of an interface display device according to an embodiment of this application; Figure 15 This is a schematic diagram of the structure of an interface display device according to an embodiment of this application. Detailed Implementation

[0013] This specification provides an interface display method, device, and storage medium through its embodiments.

[0014] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0015] The inventive concept of this application is as follows: With the rapid development of random computer technology and the widespread availability of terminal devices, the number of information elements displayed on the terminal's interface has increased dramatically when users access various business services. Due to information redundancy, excessively high contrast of visual elements, and high visibility of invalid information, this information overload easily leads to cognitive overload for users during human-computer interaction, causing visual fatigue and distraction, thereby reducing user operating efficiency and interactive experience. This is especially true for user groups such as the elderly who have slower information acquisition; the massive amount of information on the interface often leads to user operation failures, resulting in a poor operating experience and significant frustration for this user group. Younger users are also frequently affected by the information overload on the interface, forgetting their original tasks during operation, leading to low operating efficiency.

[0016] In existing technologies, some solutions attempt to detect users' biometric data using external biosensor devices (such as eye trackers and heart rate sensors) to determine if the user is in a state of cognitive overload. Once a state of cognitive overload is identified, the system adds interference noise and reduces the number of operation items in the user interface. However, this approach relies heavily on external biosensor devices, resulting in high equipment configuration costs and complex deployment. Furthermore, adding interference noise and reducing operation items can disrupt the original user interface display, leading to significant changes in the interface and impacting user behavior and business processing efficiency. In addition, the visual adjustment logic of these solutions is rigid, with fixed parameters, abrupt state transitions, and no smooth transition mechanism, which can easily cause secondary visual interference to users. To address these issues, this specification provides a technical solution that resolves the aforementioned problems. This solution determines the user's current cognitive load based on user interaction data on the user interface and assesses whether the current cognitive load meets visual optimization conditions. If the conditions are met, a target area in the user interface is identified based on the interaction data and / or the element types of the interface elements. Visual noise reduction is then applied to the interface elements in the target area using a noise reduction strategy corresponding to the user's current cognitive load. This visual noise reduction includes altering the visual presentation parameters of the interface elements to reduce visual interference from the target area. Thus, by quickly and accurately determining the user's current cognitive load based on user interaction data on the user interface, this solution avoids the high equipment configuration costs associated with relying on external biosensor devices to detect biometric data. In other words, it improves the efficiency and accuracy of recognizing the user's cognitive load while saving on configuration costs. Secondly, based on the element noise reduction strategy corresponding to the cognitive load state, visual noise reduction processing is performed on the target area identified based on interaction behavior data and / or element type. This can optimize the visual noise during user operation without changing the interface element structure, ensuring that the noise reduction intention revolves around the user's current operation intention. While reducing the user's cognitive load, it can improve the user's operation efficiency and user experience. For details, please refer to the following content.

[0017] In one embodiment, such as Figure 1 As shown in the embodiments of this specification, an interface display method is provided. This interface display method can be applied to terminal devices or servers, wherein the terminal device can be a device such as a personal computer, or a terminal device such as a mobile phone or tablet computer. The method specifically includes the following steps: In S102, based on the user's interactive behavior data on the operation interface, the user's current cognitive load state is determined, and it is judged whether the user's current cognitive load state meets the visual optimization conditions.

[0018] The user interface can be an operable interface in software or a system. The interactive behavior data can include user input data on the operation page via input devices such as touch screens, mice, and keyboards. The interactive behavior data can be obtained through the input components (such as touch screens, mice, and keyboards) built into the terminal device or server, without relying on external biometric sensors. For example, the interactive behavior data can include mouse movement trajectory, control hover position and hover duration, keyboard input rhythm and input pause duration, touch point coordinate changes, touch dwell position and touch dwell duration, pressure value, continuous swipe gesture speed and pause interval, page swipe speed, swipe direction and swipe mode, touch switching frequency of preset controls on the interface, number of fingers and movement trajectory of multiple finger combinations when operating the interface, virtual keyboard input rhythm and input pause duration, finger swipe speed, scrolling speed and direction of the interface and interface elements when dragging, distribution of reading time in the interface area, frequency of deletion (or modification), etc. The cognitive load state can include various types, such as overload type and non-overload type. Different types can be configured according to the actual application scenario. This specification does not specifically limit this in the embodiments.

[0019] In practice, taking a terminal device as an example, users can trigger an application on the terminal device by touching it with their fingers. The terminal device can collect interactive behavior data of the user when browsing each operation interface in the application. For example, the terminal device can collect interactive behavior data such as the user's page swiping speed, touch dwell time, number of control jumps within a preset time window (such as 5 seconds, 10 seconds, etc.), and touch pressure value on the operation interface.

[0020] Alternatively, taking a server as an example, a user can trigger the execution of a document editing task (or image editing task, information browsing task, etc.) on the server through input states such as mouse and keyboard. The server can collect user interaction behavior data in the document editing interface (i.e., the operation interface), such as the user's mouse movement trajectory, control hover position and hover duration, keyboard input rhythm and input pause duration, page scrolling speed and scrolling direction, and other interaction behavior data.

[0021] After collecting interaction behavior data, the terminal device or server can determine the user's current cognitive load state based on the collected interaction behavior data. For example, the terminal device or server can determine the user's current cognitive load state based on preset state judgment rules and interaction behavior data. The preset state judgment rules can be determined based on historical interaction behavior data and historical cognitive load states.

[0022] For example, based on preset state judgment rules, the cognitive load corresponding to each feature data in the interaction behavior data can be determined, and the sum (or maximum value, average value, etc.) of the cognitive load corresponding to the feature data can be determined as the user's current cognitive load (i.e. the user's current cognitive load state). Then, based on the user's current cognitive load and cognitive load threshold, it can be determined whether the user's current cognitive load state meets the visual optimization conditions.

[0023] Furthermore, the method for determining the current cognitive load state of the user described above is an optional and feasible method. In actual application scenarios, there can be a variety of different methods. Different methods can be selected according to different actual application scenarios. This specification does not specifically limit this method in the embodiments.

[0024] In S104, if the visual optimization conditions are met, the target area in the operation interface is identified based on the interaction behavior data and / or the element type of the interface elements in the operation interface.

[0025] Among them, interface elements can be visual components that enable user interaction in the operation interface. The element types of interface elements can include buttons, icons, labels, menus, etc. The target area can be the area that is not of core interest to the user, that is, the target area can be the area that needs to be visually denoised.

[0026] In practice, when visual optimization is required, the terminal device or server can identify non-core areas in the user interface, i.e., the target areas that need visual optimization, based on interaction behavior data and / or the element types of interface elements in the user interface.

[0027] For example, a terminal device or server can identify a target area based on interaction behavior data. Specifically, the terminal device or server can identify the core area of ​​interest in the operation interface based on the touch position (or cursor position) in the interaction behavior data, and determine the area in the operation interface other than the core area of ​​interest as the target area.

[0028] Alternatively, the terminal device or server can identify the target area based on the element type of the interface elements in the operation interface. Specifically, the area where preset element types such as menus and buttons are located can be determined as the target area.

[0029] Alternatively, the terminal device or server can also identify the target area based on the interaction behavior data and the element type of the interface elements in the operation interface. For example, a pre-trained region recognition model can be used to identify the target area in the operation interface based on the interaction behavior data and the element type of the interface elements in the operation interface.

[0030] Furthermore, the above-mentioned method for determining the target area is an optional and feasible method. In actual application scenarios, there can be a variety of different methods. Different methods can be selected according to different actual application scenarios. This specification does not specifically limit this method in the embodiments.

[0031] In S106, visual noise reduction is performed on the interface elements in the target area according to the element noise reduction strategy corresponding to the user's current cognitive load state.

[0032] Visual noise reduction processing may include changing the visual presentation parameters of interface elements to reduce visual interference to users in the target area. The visual presentation parameters can be used to control the display effect of interface elements.

[0033] In implementation, an interface display system can be built based on the above interface display methods, such as... Figure 2 As shown, the interface display system may include an interactive behavior acquisition module, a cognitive load state inference module, a visual softening strategy module, and an interface dynamic softening module.

[0034] Among them, the interactive behavior acquisition module can be used to collect user interactive behavior data in real time, the cognitive load state inference module can be used to classify cognitive load state based on interactive behavior data, the visual softening strategy module can be used to match element noise reduction strategy according to cognitive load state, and the interface dynamic softening module can be used to perform interface rendering adjustment in a fluid gradient manner based on element noise reduction strategy.

[0035] This specification provides an interface display method. Based on user interaction data on the interface, the method determines the user's current cognitive load state and whether it meets visual optimization conditions. If the conditions are met, a target area in the interface is identified based on the interaction data and / or the element types of the interface elements. Visual noise reduction is then performed on the interface elements in the target area according to an element noise reduction strategy corresponding to the user's current cognitive load state. This visual noise reduction includes changing the visual presentation parameters of the interface elements to reduce visual interference from the target area. Thus, by quickly and accurately determining the user's current cognitive load state based on user interaction data, this method avoids the high equipment configuration costs associated with relying on external biosensor devices to determine cognitive overload. In other words, it improves the efficiency and accuracy of cognitive load state recognition while saving on configuration costs. Secondly, based on the element noise reduction strategy corresponding to the cognitive load state, visual noise reduction processing is performed on the target area identified based on interaction behavior data and / or element type. This can optimize the visual noise during user operation without changing the interface element structure, ensuring that the noise reduction intention revolves around the user's current operation intention. While reducing the user's cognitive load, it can improve the user's operation processing efficiency and user experience.

[0036] In practical applications, the specific processing methods for determining the user's current cognitive load state based on the user's interactive behavior data on the operation interface in S102 above can vary. The following provides one optional processing method, such as... Figure 3 As shown, the specific process may include the following steps, S1022.

[0037] In S1022, a pre-trained state recognition model is used to determine the user's current cognitive load state based on interaction behavior data.

[0038] The interactive behavior data may include at least one of the following: page scrolling speed, touch dwell time, and the number of times the control jumps within a preset time window. The state recognition model may be a model built based on a preset machine learning algorithm, and the number of model parameters of the state recognition model may be less than the number of preset parameters, that is, the state recognition model may be a lightweight machine learning model.

[0039] In implementation, terminal devices or servers can use machine learning models to identify cognitive load status in real time based on interactive behavior. That is, terminal devices or servers can input the collected interactive behavior data into a pre-trained lightweight machine learning model (i.e., a pre-trained state recognition model) to extract features and analyze data from the interactive behavior data through the model, and identify and determine the user's current cognitive load status in real time.

[0040] The training process of the state recognition model includes the following steps: 1. Training data collection: Record the following relevant data of test users operating the device in various preset usage scenarios: (1) Multi-dimensional operation interaction data during operation, such as sliding speed, hovering time, input rhythm, pause interval, deletion frequency, etc.; (2) Real cognitive state load labels obtained through post-event self-evaluation.

[0041] 2. Feature preprocessing: Perform missing value processing and normalization on the multidimensional operation and interaction data to ensure that the multidimensional operation and interaction data contains temporal change information of behavioral features.

[0042] 3. Model Training: Using the multidimensional operational interaction data after feature preprocessing as described above, and the real cognitive load state labels, supervised learning training is performed on the state recognition model.

[0043] 4. Evaluation and Lightweighting: Evaluate model performance on the test set to ensure accuracy under high-load focus, and convert to a format supported by the terminal inference engine to ensure efficient operation on both mobile devices and servers.

[0044] 5. Deployment: After the pre-trained model is deployed to the terminal device (or server), it can be fine-tuned using local data through the federated learning framework with the user's authorization. This allows the fine-tuned model (i.e., the trained state recognition model) to gradually adapt to the user's personal operating habits, while the original data does not leave the local device, thus ensuring privacy and security.

[0045] During model training, the state recognition model can learn and summarize the state judgment rules corresponding to each cognitive load state. In practical applications, the pre-trained state recognition model can be used to determine the user's current cognitive load state based on interaction behavior data and the state judgment rules corresponding to each cognitive load state learned during model training.

[0046] In addition, the corresponding state judgment rules can be selected according to the type of user device, so as to use the pre-trained state recognition model, based on interaction behavior data and the state judgment rules corresponding to the type of user device, to determine the user's current cognitive load state.

[0047] For example, a user device may include a terminal device and a server. The state judgment rule corresponding to the terminal device may include state judgment rule 1, and the state judgment rule corresponding to the server may include state judgment rule 2. State judgment rule 1 can be used to determine whether the current cognitive load state is the first cognitive load state based on whether the user's page swiping speed on the terminal device (such as the page swiping speed when the user swipes the page via touch) is less than speed threshold 1. State judgment rule 2 can be used to determine whether the current cognitive load state is the first cognitive load state based on whether the user's page swiping speed on the server (such as the page swiping speed when the user controls the page with a mouse) is less than speed threshold 2. Since the page operation methods of the terminal device and the server are different, different state judgment rules can be configured for different types of user devices. For example, the speed threshold 1 mentioned above can be different from the speed threshold 2 to improve the accuracy of determining the user's current cognitive load state.

[0048] In this way, by collecting user interaction data naturally generated when using the device, such as page swiping speed and direction, touch dwell position and duration, touch pressure value, keyboard input rhythm and pause duration, deletion and modification frequency, etc., the data is extracted into multi-dimensional behavioral feature vectors and input into a pre-trained lightweight machine learning model to achieve factual inference of the user's cognitive state. This eliminates the dependence on external biosensors such as eye trackers and EEG devices, and solves the technical bottleneck that makes it difficult to promote cognitive noise reduction technology due to hardware barriers.

[0049] In practical applications, the specific processing method for determining whether the user's current cognitive load state meets the visual optimization conditions in S102 above can be varied. The cognitive load state can include a first cognitive load state and a second cognitive load state. The page scrolling speed corresponding to the first cognitive load state can be less than or equal to a first speed threshold, and the page scrolling speed corresponding to the second cognitive load state can be greater than or equal to a second speed threshold. The second speed threshold can be greater than the first speed threshold. Accordingly, the following provides an optional processing method, such as... Figure 4 As shown, the specific process may include the following step S1024.

[0050] In S1024, if the user's current cognitive load state is the first cognitive load state, it is determined that the user's current cognitive load state meets the visual optimization conditions.

[0051] In implementation, the server or terminal device can determine whether the user's current cognitive load state is the first cognitive load state based on the page scrolling speed. If the user's current cognitive load state is determined to be the first cognitive load state, it can be determined that the user's current cognitive load state meets the visual optimization conditions. That is, if the user's page scrolling speed is less than the first speed threshold, it can be determined that the user's current cognitive load state meets the visual optimization conditions.

[0052] In practical applications, there are various ways to determine whether the user's current cognitive load state meets the visual optimization conditions in the above S1024 when the user's current cognitive load state is the first cognitive load state. The following provides an optional processing method, which may include the following steps A1 to A2.

[0053] In A1, when the user's current cognitive load state is the first cognitive load state, the duration of the user's state in the first cognitive load state is counted.

[0054] In practice, to avoid invalid state switching caused by brief user misoperations or gesture shaking, the terminal device or server can count the duration of the user's state in the first cognitive load state when the user's current cognitive load state is the first cognitive load state.

[0055] In A2, if the state duration is greater than the preset duration threshold, it is determined that the user's current cognitive load state meets the visual optimization conditions.

[0056] In practice, taking a preset duration threshold of 0.5 seconds as an example, if the user's current cognitive load remains stable within 0.5 seconds, the interface softening adjustment can be initiated. This will determine that the user's current cognitive load meets the visual optimization conditions. This cognitive state buffering confirmation mechanism can effectively filter out invalid state switching caused by brief user misoperations or gesture jitter, avoid frequent interface changes, and ensure the rendering stability and naturalness of the operation interface.

[0057] In practical applications, the visual noise reduction strategy for interface elements in the target area in S106, based on the user's current cognitive load state, can be implemented in various ways. The first cognitive load state may include a first sub-state and a second sub-state. Accordingly, the following provides an optional processing method, such as... Figure 5 As shown, the specific process may include the following steps S1062 to S1064.

[0058] In step S1062, based on the mapping relationship between the user's current cognitive load state and the pre-stored element noise reduction strategy, if the user is in the first sub-state, then the element noise reduction strategy with the first noise reduction amplitude is determined to be used to perform visual noise reduction processing on the interface elements in the target area.

[0059] The mapping relationship between the user's current cognitive load state and the pre-stored element denoising strategy can be a mapping relationship built based on the historical cognitive load state and the historical element denoising strategy. Based on this pre-built mapping relationship, the element denoising strategy corresponding to the current cognitive load state can be quickly and accurately determined.

[0060] In step S1064, based on the mapping relationship between the user's current cognitive load state and the pre-stored element noise reduction strategy, if the user is in the second sub-state, then the element noise reduction strategy with the second noise reduction amplitude is determined to be used to perform visual noise reduction processing on the interface elements in the target area.

[0061] The first noise reduction amplitude can be greater than the second noise reduction amplitude.

[0062] In implementation, the first cognitive load state may also include a first sub-state and a second sub-state. The page scrolling speed corresponding to the first sub-state may be less than the page scrolling speed corresponding to the second sub-state. The first noise reduction amplitude of the element noise reduction strategy corresponding to the first sub-state may be greater than the second noise reduction amplitude of the element noise reduction strategy corresponding to the second sub-state.

[0063] For example, the first sub-state can be a high-load focused state, the second sub-state can be a stable browsing state, and the second cognitive load state can be a relaxed distracted state. That is, the terminal device or server can match a gradient-based visual weakening parameter strategy (i.e., an element noise reduction strategy with the first noise reduction amplitude) based on the user's real-time cognitive state layering results to dynamically generate corresponding interface optimization instructions, realizing the adaptive matching logic of "the higher the cognitive load, the higher the noise reduction intensity". That is, for the high-load focused state, the maximum intensity weakening parameter range can be matched to deeply weaken the visual interference of secondary interfaces; for the stable browsing state, a low intensity weakening parameter range can be matched to make only slight visual optimizations; and for the relaxed distracted state, the original interface parameters can be locked and no rendering adjustments can be performed to avoid invalid interface changes and ensure the naturalness of interface interaction.

[0064] Specifically, for the high-load focus state (i.e., the first sub-state), since the user is continuously focusing on a certain content area in the operation interface, there may be slow page scrolling speed, long touch dwell time, low focus switching frequency (i.e., the number of times the control jumps within the preset time window), and no frequent jump operations. This indicates that the user may be deeply browsing, inputting, or processing information. Redundant functional elements around the interface are prone to causing cognitive interference. At this time, the element noise reduction strategy corresponding to the first sub-state can be triggered to minimize the visual stimulation of secondary elements. Taking the terminal device as an example, the state judgment rules corresponding to the first sub-state in the terminal device can be shown in Table 1 below.

[0065] Table 1

[0066] In this way, the terminal device can use a pre-trained state recognition model, based on interactive behavior data and one or more state judgment rules in Table 1 above, to determine whether the user's current cognitive load state is the first sub-state.

[0067] For the stable browsing state (i.e., the second sub-state), the user may be performing operations such as scrolling the page at a constant speed, switching the page focus moderately, and intermittently touching and clicking controls. In other words, the user's cognitive load may be within the normal range, and there is no need for high-intensity noise reduction. A light, low-amplitude element noise reduction strategy (i.e., an element noise reduction strategy with the second noise reduction amplitude) can be triggered. This means that only a few redundant elements need to be fine-tuned to balance interface stability and light noise reduction requirements. Taking a terminal device as an example, the state judgment rules corresponding to the second sub-state in the terminal device can be shown in Table 2 below.

[0068] Table 2

[0069] In this way, the terminal device can use a pre-trained state recognition model, based on interactive behavior data and one or more state judgment rules in Table 2 above, to determine whether the user's current cognitive load state is the second sub-state.

[0070] For the loose cognitive load state (i.e., the second cognitive load state), if the user frequently switches between operation pages, quickly scrolls through the operation interface, clicks controls randomly, or stays on the page for a long time without operation, it indicates that the user may be in a state of scattered attention and no need for in-depth operation. That is, the user's current cognitive load is low and does not meet the visual optimization conditions. Therefore, the visual optimization strategy (i.e., element noise reduction strategy) can not be triggered, and the interface can remain in its original display state. Taking the terminal device as an example, the state judgment rules corresponding to the second cognitive load state in the terminal device can be shown in Table 3 below.

[0071] Table 3

[0072] In this way, the terminal device can use a pre-trained state recognition model, based on interactive behavior data and one or more state judgment rules in Table 3 above, to determine whether the user's current cognitive load state is the second cognitive load state.

[0073] Because physiological signals are collected using external sensors such as eye trackers and EEG devices, it is impossible to distinguish different types of cognitive load states. Therefore, based on user interface operation density, attention concentration, etc., the user's cognitive load state is precisely stratified, that is, to determine whether the user's current cognitive load state is a high-load focused state, a stable browsing state, or a relaxed distracted state. For example, when the user is in a high-load focused state, it can be determined that the user has a large information reception pressure on the operation interface and excessive cognitive redundancy noise. At this time, the visual softening strategy module can be triggered. Alternatively, when the user is in a relaxed distracted state, the interface can be kept unchanged to avoid ineffective visual changes to the interface. That is, full noise reduction can be triggered in the "high-load focused state", mild noise reduction can be triggered in the "stable browsing state", and the interface can be kept unchanged in the "relaxed distracted state". This solves the problem of coarse noise reduction strategy caused by simple binary state classification and ensures the accuracy of visual noise reduction processing.

[0074] In practical applications, the specific processing methods for visual noise reduction of interface elements in the target area according to the element noise reduction strategy corresponding to the user's current cognitive load state in S106 can be varied. The following provides one optional processing method, such as... Figure 6 As shown, the specific process may include the following steps S1066 to S10610.

[0075] In S1066, the region type to which the target region belongs under the user's current cognitive load state is obtained.

[0076] The area types can include background interference areas, secondary functional areas, etc.

[0077] In practice, during user operations, the user's core focus area may change due to changes in user actions. Therefore, it is possible to obtain the region type to which the target region belongs under the user's current cognitive load state.

[0078] For example, the server can determine the region type of the target area under the user's current cognitive load state based on interaction behavior data and / or the element type of interface elements in the operation interface. For example, when the user is currently in a high-load focus state (i.e., the first sub-state), the area where the user's touch dwell time is less than the first duration threshold and the element type of the interface elements is menu, button, etc. can be determined as a secondary function area, and the area where the element type of the interface elements is icon, label, etc. can be determined as a background interference area.

[0079] Alternatively, if the user is currently in a stable browsing state (i.e., the second sub-state), areas where the user's touch dwell time is less than the second duration threshold and the contained interface elements are of the menu, button, or similar type can be designated as secondary functional areas. Areas containing interface elements of the icon, label, or similar type can be designated as background interference areas. The first duration threshold can be less than the second duration threshold.

[0080] Furthermore, the method for determining the region type of the target region mentioned above is an optional and feasible method. In actual application scenarios, there can be a variety of different methods. Different methods can be selected according to different actual application scenarios. This specification does not specifically limit this method in the embodiments.

[0081] In practical applications, there are various ways to obtain the region type of the target region under the user's current cognitive load state in the above S1066. The following is an optional processing method, which may include the processing of the following step B1.

[0082] In B1, the region type to which the target region belongs under the user's current cognitive load is determined based on the correlation between the target region and the core focus region.

[0083] In implementation, the server can determine the relevance between the target area and the core area of ​​interest based on the similarity of their interactive behavior characteristics and interface elements. Based on this relevance, the server can determine the area type to which the target area belongs under the user's current cognitive load.

[0084] For example, if a user is currently in a highly focused state (i.e., the first sub-state), and the relevance between the target area and the core focus area is greater than a first relevance threshold, then the target area can be designated as a secondary functional area. Conversely, if a user is currently in a stable browsing state (i.e., the second sub-state), and the relevance between the target area and the core focus area is greater than a second relevance threshold, then the target area can be designated as a secondary functional area. The second relevance threshold can be lower than the first relevance threshold.

[0085] In S1068, the element noise reduction parameters corresponding to the target area are determined based on the element noise reduction strategy corresponding to the user's current cognitive load state and the area type of the target area.

[0086] In implementation, since different types of regions have different visual optimization needs under different cognitive load states, terminal devices or servers can determine the element denoising parameters corresponding to the target region based on the element denoising strategy corresponding to the user's current cognitive load state and the region type of the target region. For example, taking Gaussian blur parameters as an example, the Gaussian blur parameter corresponding to the secondary functional area under high-load focus state can be smaller than the Gaussian blur parameter corresponding to the background interference area under high-load focus state, or the Gaussian blur parameter corresponding to the secondary functional area under high-load focus state can be larger than the Gaussian blur parameter corresponding to the secondary functional area under stable browsing state.

[0087] In practical applications, the specific processing method for determining the element noise reduction parameters corresponding to the target area in S1068 based on the element noise reduction strategy corresponding to the user's current cognitive load state and the area type of the target area can be varied. The following provides an optional processing method, which may specifically include the processing of the following steps C1.

[0088] In C1, the element noise reduction parameters for each target region are determined based on the element noise reduction strategy corresponding to the user's current cognitive load state, the region type of each target region, and the positional relationship between target regions.

[0089] Among them, for two spatially adjacent target regions, the absolute value of the difference between the corresponding element noise reduction parameters can be less than a preset difference threshold.

[0090] In implementation, the terminal device or server can control the difference in element noise reduction parameters between two adjacent target areas to be less than a preset difference threshold, thereby achieving spatial gradient transition. That is, during visual noise reduction processing, the changes in the operating interface can be made to gradually decrease from the core focus area (i.e., the core attention area) of the user's current operation outwards, achieving "clear operation area and gradually weakened surroundings". The core focus area can maintain (or enhance) its original clarity, secondary functional areas are subjected to medium intensity visual softening, and background interference areas are subjected to maximum intensity visual softening. Furthermore, different target areas can be smoothly connected through a continuous and gradual softening field, achieving no clear boundary lines.

[0091] In S10610, within a preset consumption time, visual noise reduction processing is performed on the interface elements in the target area based on the element noise reduction parameters corresponding to the target area.

[0092] In implementation, terminal devices or servers can control the smooth transition of visual noise reduction over time. For example, when the cognitive state is determined to initiate the softening change of the interface, the visual change of the operation interface can be allowed to consume a certain amount of time (i.e., a preset consumption time, such as 1-2 seconds), so that the visual attribute value can gradually transition from the initial value to the target value along a smooth curve (such as an S-shaped curve) to avoid instantaneous switching.

[0093] In practical applications, element denoising strategies can include blurring strategies and / or parameter degradation strategies. Element denoising parameters can include Gaussian blur parameters used in the blurring strategy to control the blur level of interface elements, and / or degradation parameters used in the parameter degradation strategy to downgrade the visual parameters controlling the interface elements. Visual parameters can include interface transparency, color saturation, and brightness attenuation parameters. That is, the element denoising parameters of the element denoising strategy can include at least one of Gaussian blur parameters, interface transparency, color saturation, and brightness attenuation parameters. The above-mentioned element denoising parameters are configurable range parameters, adaptable to different device resolutions, interface scenes, interface styles, and user cognitive habits. They can adaptively fine-tune the upper and lower limits of the parameter range according to the actual application scenario to achieve differentiated interface visual weakening and cognitive denoising, and adapt to diverse software interface rendering needs.

[0094] In implementation, such as Figure 7 As shown, the terminal device or server can be in a running state, and the interface displays that the system is ready. Then, the user can operate the interface using gestures, touch, or keyboard. Next, the interface displays the system's interaction behavior acquisition module, which can collect user interaction behavior data in real time. The cognitive load state inference module can analyze the interaction behavior data using a lightweight machine learning model to determine the user's current cognitive load state. For example, it can be a high-load focused state, a stable browsing state, or a relaxed distracted state. For the high-load focused state, a full visual noise reduction strategy can be triggered; for the stable browsing state, a mild visual noise reduction strategy can be triggered; and for the relaxed distracted state, no visual noise reduction strategy can be triggered. After determining the element noise reduction strategy corresponding to the user's current cognitive load state, visual noise reduction strategy matching can be performed to determine the gradient element noise reduction parameters, such as Gaussian blur radius and color saturation. Finally, by parsing the view hierarchy, a fluid gradient mechanism can be executed to dynamically soften the interface. After visual noise reduction, user behavior data continues to be monitored so that data processing can continue based on the collected user interaction behavior data when user behavior changes.

[0095] For example, consider a user browsing an application on a terminal device, reading a long article on the topic of "XXX". The user can continuously swipe and click on the interface, and the interaction behavior collection module can collect the user's interaction behavior data in real time. Simultaneously, the cognitive load state inference module can continuously infer the user's cognitive load state.

[0096] Specifically, for example, after clicking to enter... Figure 8 When reading the article, the user's fingers may quickly swipe up and down the screen to quickly browse the general content. The page scrolling speed is fast, but there is no prolonged lingering on any paragraph. The cognitive load state inference module detects the fast page scrolling speed, frequent finger movements, and lack of sustained engagement. Therefore, the cognitive load state inference module can determine that the user is in a "loosely focused state" (i.e., the second cognitive load state), meaning the user's attention is not yet focused, the cognitive load is low, and there is no need to activate visual noise reduction strategies.

[0097] Because a user is attracted by a particular viewpoint in the article details, their finger swiping speed slows down, eventually stopping completely on a certain paragraph. The user's thumb may continuously press on a certain spot on the screen to keep the page still, and their gaze may linger on that paragraph for more than 3 seconds without clicking any controls. At this point, the cognitive load state inference module, through the interaction behavior data collected by the interaction behavior acquisition module, if the page swiping speed is close to zero, the touch dwell time exceeds a preset threshold, there is no change in interface focus, and the touch pressure value is slightly higher than usual, it can be determined that the user has entered a "high-load focus state." The element noise reduction strategies corresponding to this cognitive load state can include: 1. For background interference areas, such as advertising areas and "popular comments" preview areas, a Gaussian blur radius of 12px can be used for blurring, and the color saturation can be reduced to 15% of the original value, and the interface transparency can be reduced to 40% of the original value; 2. For secondary function areas, such as button area 1 containing preset controls for like, comment, and share, and button area 2 containing preset controls for back and favorites, a Gaussian blur radius of 4px can be used for blurring, and the color saturation can be reduced to 30% of the original value, and the interface transparency can be reduced to 50% of the original value.

[0098] Furthermore, for key areas of interest in the user interface, such as article details, no visual noise reduction processing is required, thus maintaining 100% clarity in that area.

[0099] After confirming that the user maintains a high level of focus within a preset time threshold (e.g., 1 second), the cognitive load state inference module can initiate the interface softening module. This involves performing visual noise reduction based on the element noise reduction parameters of the aforementioned visual noise reduction strategy. During interface changes, a fluid gradient mechanism can be used to perform visual softening: for example, the softening can be gradually enhanced outwards from the core text paragraph where the user's gaze is currently focused (i.e., the core focus area where the user is pressing). The text area containing article details can be fully clear, while the bottom button bar and top navigation bar can be slightly faded and blurred. The blurring level of the bottom advertisements and popular comments areas can be relatively high, and the colors can be noticeably faded. These visual changes can be completed gradually along a smooth curve within approximately 1.5 seconds, rather than instantaneously. This prevents the user from feeling that the interface has "suddenly changed," instead allowing non-core information to naturally "recede to the background." The changing areas can be as follows: Figure 9 As shown.

[0100] After reading the main text, users can swipe their fingers to the comment section and linger there for an extended period. This indicates a high level of cognitive load, suggesting the user is highly focused on reading the comments. Because the target area (and its type) changes, the visual softening strategy module can implement new visual noise reduction strategies to readjust the interface for background interference areas and secondary functional areas. The changed areas can be as follows: Figure 10 As shown.

[0101] In addition, when the cognitive load state inference module detects that the user's current cognitive load state has changed to a second cognitive load state, it can perform visual restoration processing on the target area.

[0102] Alternatively, taking a user's use of an online collaborative document tool via a server to write a project completion report as an example, when the user opens the document editing interface (i.e., the operation interface), the user can quickly scroll up and down to browse the completed parts using the mouse wheel. At this time, the mouse pointer moves relatively quickly on the operation interface, and the user can also click the sidebar at a lower frequency to view the activities of collaborating members. The keyboard may not be used for input. The interaction behavior data collected by the interaction behavior collection module may include: 1. The mouse wheel scrolls quickly and frequently changes direction (e.g., scroll up → scroll down → scroll up again). 2. The mouse pointer movement covers a larger area, such as moving from the main text area to the sidebar and then to the toolbar; 3. Keyboard input interval: No input data; 4. Frequency of deletion or modification: No modification behavior.

[0103] Based on the above interaction data, the cognitive load state inference module can determine that the user is currently in a "relaxed and distracted state" with a low cognitive load. The visual softening strategy module can then avoid triggering visual softening processing, and the user interface can maintain its original display state, with all functional areas fully visible, allowing the user to freely switch attention.

[0104] When a user navigates to the "Conclusions and Recommendations" section of a document and needs to rewrite this section, the user might rapidly type on the keyboard, occasionally using the arrow keys to fine-tune the cursor position or selecting text with the mouse to adjust formatting. In this case, the interaction behavior data collected by the interaction behavior acquisition module can include: 1. Keyboard input frequency: Continuous character input with a stable interval of 80-150ms between characters, and each continuous input segment lasting 20-40 seconds; 2. Input pause duration: The pause duration between consecutive input segments is approximately 2-5 seconds (which may be a short pause to think about the next sentence); 3. Frequency of deletion or modification: Low; occasionally, the backspace key is used to correct typos. 4. Cursor movement: Occasionally use the arrow keys to fine-tune the cursor within a paragraph, but there are no large jumps; 5. Mouse behavior: The mouse is basically still, and the pointer stays in a blank area of ​​the page or an irrelevant area.

[0105] Based on the above interactive behavior data, the cognitive load state inference module can infer that the current user's input rhythm is stable, the pauses are short, and the modification rate is low, which may indicate that the user is in a smooth output state. The module can determine that the user's current cognitive load state is "stable browsing state", that is, the cognitive load is in the normal range at this time.

[0106] The element noise reduction strategy corresponding to this cognitive load state can trigger a slight visual softening. For example, the color saturation of the right-side collaborator sidebar of the operation interface can be slightly reduced (e.g., reduced to 70% of the original value), and the transparency of the top promotion bar can also be slightly reduced (e.g., reduced to 75% of the original value), while the text area and formatting toolbar can remain clear. That is, under the current cognitive load state, the area where the right-side collaborator sidebar and the top promotion bar are located can be the target area.

[0107] Additionally, when a change in user behavior is detected, such as starting four minutes after the user interface is launched, the user may need to argue a complex technical conclusion but is unsure of the wording. In this case, the user's behavior pattern may change significantly. That is, the interaction behavior data collected by the current interaction behavior collection module may include: 1. Input pause duration: The continuous input segment becomes shorter (e.g., 5-8 seconds), and the pause interval becomes much longer (e.g., 15-30 seconds or even longer); 2. Deletion or modification frequency: The frequency of backspace key use increases sharply, and the same paragraph is repeatedly deleted and rewritten (e.g., "System performance improved..." → deleted everything → "Overall system performance..." → deleted again → pause). 3. Cursor movement: The cursor moves frequently and slightly within the same difficult paragraph (e.g., the arrow keys can be used to adjust the cursor position back and forth). 4. Mouse behavior: The mouse hovers over a paragraph in the document for a long time without any operation (indicating that the user is thinking and reading deeply), and occasionally the pointer moves slightly without any purpose (which may be a subconscious behavior of the user when thinking).

[0108] Based on the combination of the above interactive behavior data (i.e., a sharp increase in input pauses, high frequency of deletion and modification, long mouse hovering, cursor hovering in the same area, etc.), the cognitive load state inference module can determine that the user may be highly focused on processing complex information, but has difficulty outputting, and cognitive load is increasing. Therefore, it can be determined that the user is currently in a "high-load focus state".

[0109] The server can use the cognitive state buffer confirmation mechanism to start the subsequent visual noise reduction process. The interface displays that the system can confirm that the user is in this state within a preset buffer time of 1.2 seconds (to exclude the situation where the user continues to type smoothly after a brief pause in input) before starting the visual noise reduction process.

[0110] The server can use a maximum-intensity element denoising strategy that matches the "high-load focus state" and obtain the corresponding element denoising parameters. For example, the element denoising parameters for different types of target regions under the current user's cognitive load state may include: 1. For background interference areas (such as the collaborator sidebar, version history prompt card, member promotion bar, etc.): the Gaussian blur radius can be reduced by 10px, the color saturation can be reduced to 15% of the original value, and the interface transparency can be reduced to 35% of the original value.

[0111] 2. For secondary function areas (such as the top formatting toolbar): the Gaussian blur radius can be 3px, the color saturation can be reduced to 55% of the original value, and the interface transparency can be reduced to 70% of the original value.

[0112] In addition, such as Figure 11 As shown, the user's core focus area (such as the document text editing area) can maintain 100% clarity without any softening. Alternatively, the core focus area can be visually enhanced according to the user's actual needs, such as increasing the color saturation of the area.

[0113] In practical applications, after visual noise reduction processing, the visual parameters of interface elements in the target area can be updated. There are various methods for updating these visual parameters; one optional method is provided below. Figure 12 As shown, the specific process may include the following steps, S1202.

[0114] In S1202, after completing the visual noise reduction processing of the visual presentation parameters of the interface elements in the target area, if it is not detected that the user has exited the first cognitive load state and the duration of the first cognitive load state is greater than the preset duration threshold, the visual presentation parameters of the interface elements in the target area are adjusted based on the preset parameter adjustment range.

[0115] In practice, after visual noise reduction processing of interface elements in the target area, if the user is not detected to have exited the first cognitive load state and the duration of the first cognitive load state is greater than the preset duration threshold, the interface can be fine-tuned based on the preset parameter adjustment range. That is, when the user is in a static and focused state for a long time, the interface can maintain a soft visual breathing feeling by periodically fluctuating weak visual parameters (such as small fluctuations in interface transparency and brightness) to avoid a rigid static lock.

[0116] In this way, a fluid gradient mechanism (i.e., a state-awareness buffer confirmation mechanism, a time-smooth transition mechanism, a spatial gradient transition mechanism, and the aforementioned breathing fine-tuning mechanism) can be used to execute the element noise reduction strategy, so as to dynamically adjust the visual parameters of the operation interface, avoid interference problems such as instantaneous changes, flickering and jumping of the interface, and ensure that the visual adjustment is smooth, imperceptible, and in line with the user's operating habits. That is, through the synergistic cooperation of the cognitive state buffer confirmation mechanism, the time-smooth transition mechanism, the spatial gradient transition mechanism, and the aforementioned breathing fine-tuning mechanism, the problems of strong intrusion, dependence on external hardware, abrupt visual switching, and poor cross-scene adaptability in existing interface cognitive noise reduction solutions are solved. It can achieve imperceptible, adaptive, and universal intelligent noise reduction processing of cognitive noise of the operation interface.

[0117] In addition, by employing multi-dimensional visual softening techniques such as Gaussian blur, color saturation attenuation, and transparency adjustment at the input end (i.e., terminal device or server), and integrating a thought-fluid gradual execution framework of state buffer confirmation, time smoothing, spatial gradient, and breathing fine-tuning, non-core areas can be visually softened in a continuous gradient manner without changing the element structure of the operation interface. This solves the drawbacks of previous interface adjustments that were abrupt and changed the original structure and content of the interface.

[0118] In practical applications, the specific processing method for identifying the target area in the operation interface based on the interaction behavior data and / or the element type of the interface elements in S104 can be varied. The following provides one optional processing method, such as... Figure 13 As shown, the specific process may include the following steps S1042 to S1046.

[0119] In S1042, the operation interface is divided into multiple sub-regions based on the view hierarchy and control properties of the operation interface.

[0120] In implementation, terminal devices or servers can use a pre-trained region segmentation model to divide the user interface into regions based on the view hierarchy and control attributes of the user interface, resulting in multiple sub-regions. The region segmentation model can be a model built based on a preset deep learning algorithm.

[0121] In S1044, the user's core focus area is determined based on the interaction behavior data and / or the element type of the interface elements in the operation interface.

[0122] In practice, terminal devices or servers can identify the core areas of user attention in the user interface based on interactive behavior data and / or the element types of interface elements in the user interface. For example, the core areas of attention can be determined based on the user's mouse (or touch) movement trajectory and the element types of interface elements related to that movement trajectory.

[0123] In S1046, among multiple sub-regions, the region whose correlation with the core region of interest is less than a preset correlation threshold is identified as the target region.

[0124] In implementation, terminal devices or servers can determine the relevance between each sub-region and the core area of ​​interest based on the positional relationship, interface element similarity, and regional intent relevance between each sub-region and the core area of ​​interest, so as to identify the area with a relevance of less than a preset relevance threshold as the target area.

[0125] The UI dynamic softening module first uses a UI automation framework to analyze the view hierarchy and control attributes of the current interface in real time. Based on the analysis results, it divides the interface into multiple sub-regions. Then, it determines the core focus area based on interaction data and / or the element types of interface elements. From these sub-regions, it identifies the target area requiring visual optimization. In other words, the module can identify the core focus area, secondary functional areas, and background interference areas in the interface, providing a regional basis for differentiated visual softening processing. Furthermore, the same target area may be classified into different types under different cognitive load states to ensure that noise reduction always revolves around the user's current operational intent.

[0126] This specification provides an interface display method. Based on user interaction data on the interface, the method determines the user's current cognitive load state and whether it meets visual optimization conditions. If the conditions are met, a target area in the interface is identified based on the interaction data and / or the element types of the interface elements. Visual noise reduction is then performed on the interface elements in the target area according to an element noise reduction strategy corresponding to the user's current cognitive load state. This visual noise reduction includes changing the visual presentation parameters of the interface elements to reduce visual interference from the target area. Thus, by quickly and accurately determining the user's current cognitive load state based on user interaction data, this method avoids the high equipment configuration costs associated with relying on external biosensor devices to determine cognitive overload. In other words, it improves the efficiency and accuracy of cognitive load state recognition while saving on configuration costs. Secondly, based on the element noise reduction strategy corresponding to the cognitive load state, visual noise reduction processing is performed on the target area identified based on interaction behavior data and / or element type. This can optimize the visual noise during user operation without changing the interface element structure, ensuring that the noise reduction intention revolves around the user's current operation intention. While reducing the user's cognitive load, it can improve the user's operation processing efficiency and user experience.

[0127] In another embodiment, the above is an interface display method provided by the embodiments of this specification. Based on the same idea, the embodiments of this specification also provide an interface display device, which is applied to an optical transmission network, such as... Figure 14 As shown.

[0128] The interface display device includes: a status recognition module 1401, a region recognition module 1402, and a visual noise reduction module 1403, wherein: The state recognition module 1401 is used to determine the current cognitive load state of the user based on the user's interactive behavior data on the operation interface, and to determine whether the current cognitive load state of the user meets the visual optimization conditions. The region recognition module 1402 is used to identify the target region in the operation interface based on the interaction behavior data and / or the element type of the interface elements in the operation interface if it is determined that the visual optimization conditions are met. The visual noise reduction module 1403 is used to perform visual noise reduction processing on interface elements in the target area according to the element noise reduction strategy corresponding to the user's current cognitive load state. The visual noise reduction processing includes changing the visual presentation parameters of the interface elements to reduce the visual interference of the target area on the user.

[0129] In this embodiment of the specification, the state recognition module 1401 is used for: Using a pre-trained state recognition model, the user's current cognitive load state is determined based on the interaction behavior data, wherein the interaction behavior data includes at least one of the following: page scrolling speed, touch dwell time, and the number of control jumps within a preset time window.

[0130] In this embodiment of the specification, the cognitive load state includes a first cognitive load state and a second cognitive load state, wherein the page scrolling speed corresponding to the first cognitive load state is less than or equal to a first speed threshold, the page scrolling speed corresponding to the second cognitive load state is greater than or equal to a second speed threshold, and the second speed threshold is greater than the first speed threshold. The state recognition module 1401 is used for: If the user's current cognitive load state is the first cognitive load state, then the user's current cognitive load state is determined to satisfy the visual optimization condition.

[0131] In the embodiments described in this specification, the first cognitive load state includes a first sub-state and a second sub-state. The visual noise reduction module 1403 is used for: Based on the mapping relationship between the user's current cognitive load state and the pre-stored element noise reduction strategy, if the user is in the first sub-state, then it is determined that the element noise reduction strategy with the first noise reduction amplitude is adopted to perform visual noise reduction processing on the interface elements in the target area. Based on the mapping relationship between the user's current cognitive load state and the pre-stored element noise reduction strategy, if the user is in the second sub-state, then the element noise reduction strategy with the second noise reduction amplitude is determined to be used to perform visual noise reduction processing on the interface elements in the target area. Wherein, the first noise reduction amplitude is greater than the second noise reduction amplitude.

[0132] In this embodiment of the specification, the state recognition module 1401 is used for: When the user's current cognitive load state is the first cognitive load state, the duration of the user's state in the first cognitive load state is counted. If the duration of the state is greater than a preset duration threshold, then it is determined that the user's current cognitive load state meets the visual optimization conditions.

[0133] In the embodiments described in this specification, the visual noise reduction module 1403 is used for: Obtain the region type to which the target region belongs under the user's current cognitive load state; Based on the element denoising strategy corresponding to the user's current cognitive load state and the region type of the target region, determine the element denoising parameters corresponding to the target region; Within a preset time limit, visual noise reduction is performed on the interface elements in the target area based on the element noise reduction parameters corresponding to the target area.

[0134] In the embodiments of this specification, the element noise reduction strategy includes a blurring strategy and / or a parameter degradation strategy. The element noise reduction parameters include a Gaussian blur parameter used in the blurring strategy to control the blurring degree of interface elements, and / or a degradation parameter used in the parameter degradation strategy to degrade the visual parameters controlling the interface elements. The visual parameters include at least one of interface transparency, color saturation, and brightness attenuation parameters.

[0135] In the embodiments of this specification, the target region includes multiple regions, and the visual noise reduction module 1403 is used for: Based on the element denoising strategy corresponding to the user's current cognitive load state, the region type of each target region, and the positional relationship between the target regions, the element denoising parameters corresponding to each target region are determined. For two spatially adjacent target regions, the absolute value of the difference between their corresponding element denoising parameters is less than a preset difference threshold.

[0136] In the embodiments described in this specification, the device further includes: The parameter update module is used to adjust the visual presentation parameters of the interface elements in the target area based on a preset parameter adjustment range after completing the visual noise reduction processing of the visual presentation parameters of the interface elements in the target area. If it is not detected that the user has exited the first cognitive load state and the duration of the state in the first cognitive load state is greater than a preset duration threshold, the module will adjust the visual presentation parameters of the interface elements in the target area based on a preset parameter adjustment range.

[0137] In this embodiment of the specification, the region identification module 1402 is used for: Based on the view hierarchy and control properties of the operation interface, the operation interface is divided into multiple sub-regions. Based on the interaction behavior data and / or the element types of interface elements in the operation interface, determine the user's core focus area; The region among the multiple sub-regions whose correlation with the core region of interest is less than a preset correlation threshold is identified as the target region.

[0138] In the embodiments described in this specification, the visual noise reduction module 1403 is used for: Based on the correlation between the target region and the core focus region, the region type to which the target region belongs under the user's current cognitive load state is determined.

[0139] This specification provides an interface display device that determines the user's current cognitive load state based on user interaction data on the interface and determines whether the user's current cognitive load state meets visual optimization conditions. If the visual optimization conditions are met, a target area in the interface is identified based on the interaction data and / or the element types of interface elements. Visual noise reduction processing is then performed on the interface elements in the target area according to an element noise reduction strategy corresponding to the user's current cognitive load state. This visual noise reduction processing includes changing the visual presentation parameters of the interface elements to reduce visual interference from the target area to the user. Thus, firstly, based on user interaction data on the interface, the user's current cognitive load state can be quickly and accurately determined. This avoids the high equipment configuration cost associated with determining whether a user is in a state of cognitive overload using biometric data detected by external biosensor devices. In other words, it can improve the efficiency and accuracy of recognizing the user's cognitive load state while saving configuration costs. Secondly, based on the element noise reduction strategy corresponding to the cognitive load state, visual noise reduction processing is performed on the target area identified based on interaction behavior data and / or element type. This can optimize the visual noise during user operation without changing the interface element structure, ensuring that the noise reduction intention revolves around the user's current operation intention. While reducing the user's cognitive load, it can improve the user's operation processing efficiency and user experience.

[0140] In another embodiment, based on the same idea, this specification also provides an interface display device, such as... Figure 15 As shown.

[0141] Interface display devices can vary significantly due to differences in configuration or performance. They may include one or more processors 1501 and memory 1502, with memory 1502 storing one or more application programs or data. Memory 1502 can be temporary or persistent storage. The application programs stored in memory 1502 may include one or more modules (not shown), each module including a series of computer-executable instructions for the interface display device. Furthermore, processor 1501 may be configured to communicate with memory 1502 and execute the series of computer-executable instructions stored in memory 1502 on the interface display device. The interface display device may also include one or more power supplies 1503, one or more wired or wireless network interfaces 1504, one or more input / output interfaces 1505, and one or more keyboards 1506.

[0142] Specifically, in this embodiment, the interface display device includes a memory and one or more programs, wherein one or more programs are stored in the memory, and one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the interface display device, and is configured to be executed by one or more processors. The one or more programs include computer-executable instructions for performing the following: Based on the user's interactive behavior data on the operation interface, determine the user's current cognitive load state and determine whether the user's current cognitive load state meets the visual optimization conditions. If the visual optimization conditions are met, the target area in the operation interface is identified based on the interaction behavior data and / or the element type of the interface elements in the operation interface. Based on the element noise reduction strategy corresponding to the user's current cognitive load state, visual noise reduction processing is performed on the interface elements in the target area. The visual noise reduction processing includes changing the visual presentation parameters of the interface elements to reduce the visual interference of the target area on the user.

[0143] Optionally, determining the user's current cognitive load state based on the user's interactive behavior data on the user interface includes: Using a pre-trained state recognition model, the user's current cognitive load state is determined based on the interaction behavior data, wherein the interaction behavior data includes at least one of the following: page scrolling speed, touch dwell time, and the number of control jumps within a preset time window.

[0144] Optionally, the cognitive load state includes a first cognitive load state and a second cognitive load state, wherein the page scrolling speed corresponding to the first cognitive load state is less than or equal to a first speed threshold, the page scrolling speed corresponding to the second cognitive load state is greater than or equal to a second speed threshold, and the second speed threshold is greater than the first speed threshold. The step of determining whether the user's current cognitive load state meets the visual optimization conditions includes: If the user's current cognitive load state is the first cognitive load state, then the user's current cognitive load state is determined to satisfy the visual optimization condition.

[0145] Optionally, the first cognitive load state includes a first sub-state and a second sub-state. The step of performing visual noise reduction processing on interface elements in the target area according to the element noise reduction strategy corresponding to the user's current cognitive load state includes: Based on the mapping relationship between the user's current cognitive load state and the pre-stored element noise reduction strategy, if the user is in the first sub-state, then it is determined that the element noise reduction strategy with the first noise reduction amplitude is adopted to perform visual noise reduction processing on the interface elements in the target area. Based on the mapping relationship between the user's current cognitive load state and the pre-stored element noise reduction strategy, if the user is in the second sub-state, then the element noise reduction strategy with the second noise reduction amplitude is determined to be used to perform visual noise reduction processing on the interface elements in the target area. Wherein, the first noise reduction amplitude is greater than the second noise reduction amplitude.

[0146] Optionally, determining that the user's current cognitive load state satisfies the visual optimization condition when the user's current cognitive load state is the first cognitive load state includes: When the user's current cognitive load state is the first cognitive load state, the duration of the user's state in the first cognitive load state is counted. If the duration of the state is greater than a preset duration threshold, then it is determined that the user's current cognitive load state meets the visual optimization conditions.

[0147] Optionally, the step of performing visual noise reduction processing on interface elements in the target area according to the element noise reduction strategy corresponding to the user's current cognitive load state includes: Obtain the region type to which the target region belongs under the user's current cognitive load state; Based on the element denoising strategy corresponding to the user's current cognitive load state and the region type of the target region, determine the element denoising parameters corresponding to the target region; Within a preset time limit, visual noise reduction is performed on the interface elements in the target area based on the element noise reduction parameters corresponding to the target area.

[0148] Optionally, the element noise reduction strategy includes a blurring strategy and / or a parameter degradation strategy. The element noise reduction parameters include a Gaussian blur parameter in the blurring strategy used to control the blurring degree of interface elements, and / or a degradation parameter in the parameter degradation strategy used to degrade the visual parameters controlling the interface elements. The visual parameters include at least one of interface transparency, color saturation, and brightness attenuation parameters.

[0149] Optionally, the target region includes multiple regions, and determining the element denoising parameters corresponding to the target region based on the element denoising strategy corresponding to the user's current cognitive load state and the region type of the target region includes: Based on the element denoising strategy corresponding to the user's current cognitive load state, the region type of each target region, and the positional relationship between the target regions, the element denoising parameters corresponding to each target region are determined. For two spatially adjacent target regions, the absolute value of the difference between their corresponding element denoising parameters is less than a preset difference threshold.

[0150] Optionally, the method further includes: After completing the visual noise reduction processing of the visual presentation parameters of the interface elements in the target area, if it is not detected that the user has exited the first cognitive load state and the duration of the state in the first cognitive load state is greater than a preset duration threshold, then the visual presentation parameters of the interface elements in the target area are adjusted based on a preset parameter adjustment range.

[0151] Optionally, identifying the target area in the operation interface based on the interaction behavior data and / or the element type of the interface elements in the operation interface includes: Based on the view hierarchy and control properties of the operation interface, the operation interface is divided into multiple sub-regions. Based on the interaction behavior data and / or the element types of interface elements in the operation interface, determine the user's core focus area; The region among the multiple sub-regions whose correlation with the core region of interest is less than a preset correlation threshold is identified as the target region.

[0152] Optionally, obtaining the region type to which the target region belongs under the user's current cognitive load state includes: Based on the correlation between the target region and the core focus region, the region type to which the target region belongs under the user's current cognitive load state is determined.

[0153] This specification provides an interface display device that determines the user's current cognitive load state based on user interaction data on the interface and determines whether the user's current cognitive load state meets visual optimization conditions. If the visual optimization conditions are met, a target area in the interface is identified based on the interaction data and / or the element types of the interface elements. Visual noise reduction processing is then performed on the interface elements in the target area according to an element noise reduction strategy corresponding to the user's current cognitive load state. This visual noise reduction processing includes changing the visual presentation parameters of the interface elements to reduce visual interference from the target area to the user. Thus, firstly, based on user interaction data on the interface, the user's current cognitive load state can be quickly and accurately determined. This avoids the high equipment configuration cost associated with determining whether a user is in a state of cognitive overload using biometric data detected by external biosensor devices. In other words, it can improve the efficiency and accuracy of recognizing the user's cognitive load state while saving configuration costs. Secondly, based on the element noise reduction strategy corresponding to the cognitive load state, visual noise reduction processing is performed on the target area identified based on interaction behavior data and / or element type. This can optimize the visual noise during user operation without changing the interface element structure, ensuring that the noise reduction intention revolves around the user's current operation intention. While reducing the user's cognitive load, it can improve the user's operation processing efficiency and user experience.

[0154] Furthermore, based on the above Figures 1 to 13 The method shown in this specification, along with one or more embodiments, also provides a storage medium for storing computer-executable instruction information. In one specific embodiment, the storage medium can be a USB flash drive, optical disc, hard disk, etc. When the computer-executable instruction information stored in the storage medium is executed by a processor, it can achieve the following process: Based on the user's interactive behavior data on the operation interface, determine the user's current cognitive load state and determine whether the user's current cognitive load state meets the visual optimization conditions. If the visual optimization conditions are met, the target area in the operation interface is identified based on the interaction behavior data and / or the element type of the interface elements in the operation interface. Based on the element noise reduction strategy corresponding to the user's current cognitive load state, visual noise reduction processing is performed on the interface elements in the target area. The visual noise reduction processing includes changing the visual presentation parameters of the interface elements to reduce the visual interference of the target area on the user.

[0155] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the above-described storage medium embodiment is basically similar to the method embodiment, so the description is relatively simple; relevant parts can be referred to the description of the method embodiment.

[0156] This specification provides a computer-readable storage medium that determines a user's current cognitive load state based on user interaction data on an interface, and determines whether the user's current cognitive load state meets visual optimization conditions. If the visual optimization conditions are met, a target area in the interface is identified based on the interaction data and / or the element types of interface elements. Visual noise reduction processing is then performed on the interface elements in the target area according to an element noise reduction strategy corresponding to the user's current cognitive load state. This visual noise reduction processing includes changing the visual presentation parameters of the interface elements to reduce visual interference from the target area to the user. Thus, firstly, based on user interaction data on the interface, the user's current cognitive load state can be quickly and accurately determined. This avoids the high equipment configuration cost associated with determining whether a user is in a state of cognitive overload using biometric data detected by external biosensor devices. In other words, it can improve the efficiency and accuracy of recognizing the user's cognitive load state while saving configuration costs. Secondly, based on the element noise reduction strategy corresponding to the cognitive load state, visual noise reduction processing is performed on the target area identified based on interaction behavior data and / or element type. This can optimize the visual noise during user operation without changing the interface element structure, ensuring that the noise reduction intention revolves around the user's current operation intention. While reducing the user's cognitive load, it can improve the user's operation processing efficiency and user experience.

[0157] Furthermore, based on the above Figures 1 to 13 The method shown in this specification, along with one or more embodiments, also provides a computer program product including a computer program that, when executed by a processor, performs the following process: Based on the user's interactive behavior data on the operation interface, determine the user's current cognitive load state and determine whether the user's current cognitive load state meets the visual optimization conditions. If the visual optimization conditions are met, the target area in the operation interface is identified based on the interaction behavior data and / or the element type of the interface elements in the operation interface. Based on the element noise reduction strategy corresponding to the user's current cognitive load state, visual noise reduction processing is performed on the interface elements in the target area. The visual noise reduction processing includes changing the visual presentation parameters of the interface elements to reduce the visual interference of the target area on the user.

[0158] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the above-described embodiment of a computer program product is relatively simple in description because it is fundamentally similar to the method embodiment; relevant parts can be referred to the description of the method embodiment.

[0159] This specification provides a computer program product that determines a user's current cognitive load state based on user interaction data on an interface, and determines whether the user's current cognitive load state meets visual optimization conditions. If the visual optimization conditions are met, a target area in the interface is identified based on the interaction data and / or the element types of interface elements. Visual noise reduction processing is then performed on the interface elements in the target area according to an element noise reduction strategy corresponding to the user's current cognitive load state. This visual noise reduction processing includes changing the visual presentation parameters of the interface elements to reduce visual interference from the target area to the user. Thus, firstly, based on user interaction data on the interface, the user's current cognitive load state can be quickly and accurately determined. This avoids the high equipment configuration cost associated with determining whether a user is in a state of cognitive overload using biometric data detected by external biosensor devices. In other words, it can improve the efficiency and accuracy of recognizing the user's cognitive load state while saving configuration costs. Secondly, based on the element noise reduction strategy corresponding to the cognitive load state, visual noise reduction processing is performed on the target area identified based on interaction behavior data and / or element type. This can optimize the visual noise during user operation without changing the interface element structure, ensuring that the noise reduction intention revolves around the user's current operation intention. While reducing the user's cognitive load, it can improve the user's operation processing efficiency and user experience.

[0160] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0161] In the 1990s, improvements to a technology could be clearly distinguished as either hardware improvements (e.g., improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the methodology). However, with technological advancements, many methodological improvements today can be considered direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved methodology into the hardware circuit. Therefore, it cannot be said that a methodological improvement cannot be implemented using hardware physical modules. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit whose logic function is determined by the user programming the device. Designers can program and "integrate" a digital system onto a PLD themselves, without needing chip manufacturers to design and manufacture dedicated integrated circuit chips. Furthermore, nowadays, instead of manually manufacturing integrated circuit chips, this programming is mostly implemented using "logic compiler" software. Similar to the software compiler used in program development, the original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There are many HDLs, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also understand that by simply performing some logic programming on the method flow using one of these hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logical method flow can be easily obtained.

[0162] The controller can be implemented in any suitable manner. For example, it can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers, and embedded microcontrollers. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicon Labs C8051F320. A memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art will also recognize that, in addition to implementing the controller in purely computer-readable program code form, the same functionality can be achieved by logically programming the method steps to make the controller take the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the means included therein for implementing various functions can also be considered as structures within the hardware component. Alternatively, the means for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0163] For ease of description, the above apparatus is described by dividing it into various functional units. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0164] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0165] The embodiments described herein are illustrated with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable interface display device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable interface display device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0166] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0167] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, one or more embodiments of this specification may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, one or more embodiments of this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0168] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0169] The above description is merely an embodiment of this specification and is not intended to limit this specification. Various modifications and variations can be made to this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for displaying an interface, the method comprising: Based on the user's interactive behavior data on the operation interface, determine the user's current cognitive load state and determine whether the user's current cognitive load state meets the visual optimization conditions. If the visual optimization conditions are met, the target area in the operation interface is identified based on the interaction behavior data and / or the element type of the interface elements in the operation interface. Based on the element noise reduction strategy corresponding to the user's current cognitive load state, visual noise reduction processing is performed on the interface elements in the target area. The visual noise reduction processing includes changing the visual presentation parameters of the interface elements to reduce the visual interference of the target area on the user.

2. The method according to claim 1, wherein determining the user's current cognitive load state based on the user's interactive behavior data on the operating interface includes: Using a pre-trained state recognition model, the user's current cognitive load state is determined based on the interaction behavior data, wherein the interaction behavior data includes at least one of the following: page scrolling speed, touch dwell time, and the number of control jumps within a preset time window.

3. The method according to claim 2, wherein the cognitive load state includes a first cognitive load state and a second cognitive load state, wherein, The page scrolling speed corresponding to the first cognitive load state is less than or equal to a first speed threshold, the page scrolling speed corresponding to the second cognitive load state is greater than or equal to a second speed threshold, and the second speed threshold is greater than the first speed threshold. The step of determining whether the user's current cognitive load state meets the visual optimization conditions includes: If the user's current cognitive load state is the first cognitive load state, then the user's current cognitive load state is determined to satisfy the visual optimization condition.

4. The method according to claim 3, wherein the first cognitive load state includes a first sub-state and a second sub-state. The step of performing visual noise reduction processing on interface elements in the target area according to the element noise reduction strategy corresponding to the user's current cognitive load state includes: Based on the mapping relationship between the user's current cognitive load state and the pre-stored element noise reduction strategy, if the user is in the first sub-state, then it is determined that the element noise reduction strategy with the first noise reduction amplitude is adopted to perform visual noise reduction processing on the interface elements in the target area. Based on the mapping relationship between the user's current cognitive load state and the pre-stored element noise reduction strategy, if the user is in the second sub-state, then the element noise reduction strategy with the second noise reduction amplitude is determined to be used to perform visual noise reduction processing on the interface elements in the target area. Wherein, the first noise reduction amplitude is greater than the second noise reduction amplitude.

5. The method according to claim 3, wherein determining that the user's current cognitive load state satisfies the visual optimization condition when the user's current cognitive load state is the first cognitive load state includes: When the user's current cognitive load state is the first cognitive load state, the duration of the user's state in the first cognitive load state is counted. If the duration of the state is greater than a preset duration threshold, then it is determined that the user's current cognitive load state meets the visual optimization conditions.

6. The method according to claim 1, wherein performing visual noise reduction processing on interface elements in the target area according to the element noise reduction strategy corresponding to the user's current cognitive load state includes: Obtain the region type to which the target region belongs under the user's current cognitive load state; Based on the element denoising strategy corresponding to the user's current cognitive load state and the region type of the target region, determine the element denoising parameters corresponding to the target region; Within a preset time limit, visual noise reduction is performed on the interface elements in the target area based on the element noise reduction parameters corresponding to the target area.

7. The method according to claim 6, wherein the element noise reduction strategy includes a blurring strategy and / or a parameter degradation strategy, wherein the element noise reduction parameters include a Gaussian blur parameter in the blurring strategy used to control the blurring degree of interface elements, and / or a degradation parameter in the parameter degradation strategy used to degrade the visual parameters controlling the interface elements, wherein the visual parameters include at least one of interface transparency, color saturation, and brightness attenuation parameters.

8. The method according to claim 6, wherein the target region includes multiple regions, and determining the element denoising parameters corresponding to the target region based on the element denoising strategy corresponding to the user's current cognitive load state and the region type of the target region includes: Based on the element denoising strategy corresponding to the user's current cognitive load state, the region type of each target region, and the positional relationship between the target regions, the element denoising parameters corresponding to each target region are determined. For two spatially adjacent target regions, the absolute value of the difference between their corresponding element denoising parameters is less than a preset difference threshold.

9. The method according to claim 3, further comprising: After completing the visual noise reduction processing of the visual presentation parameters of the interface elements in the target area, if it is not detected that the user has exited the first cognitive load state and the duration of the state in the first cognitive load state is greater than a preset duration threshold, then the visual presentation parameters of the interface elements in the target area are adjusted based on a preset parameter adjustment range.

10. The method according to claim 6, wherein identifying the target area in the operation interface based on the interaction behavior data and / or the element type of the interface elements in the operation interface includes: Based on the view hierarchy and control properties of the operation interface, the operation interface is divided into multiple sub-regions. Based on the interaction behavior data and / or the element types of interface elements in the operation interface, determine the user's core focus area; The region among the multiple sub-regions whose correlation with the core region of interest is less than a preset correlation threshold is identified as the target region.

11. The method according to claim 10, wherein obtaining the region type to which the target region belongs under the user's current cognitive load state includes: Based on the correlation between the target region and the core focus region, the region type to which the target region belongs under the user's current cognitive load state is determined.

12. An interface display device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of an interface display method as described in any one of claims 1 to 11.

13. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of an interface display method as described in any one of claims 1 to 11.

14. A computer program product, characterized in that, It includes a computer program that, when executed by a processor, implements the steps of an interface display method according to any one of claims 1 to 11.

Images