Interface layout recommendation method for intelligent equipment

Abstract

The invention discloses an interface layout recommendation method for intelligent equipment, which relates to the technical field of interface layout, and comprises the following steps: acquiring user behavior data, and establishing a user behavior model according to the user behavior data; constructing a user time sequence behavior model reflecting the current use habits and preferences of the user; according to multi-dimensional data in the user behavior data, calculating an importance score of each interface element by adopting a weighted integral algorithm; reordering and reconstructing the page controls according to the importance scores of the interface elements; adjusting the word size of each interface element in combination with the historical word size use behavior of the user, increasing the word size of the interface element with high importance score, and reducing the word size of the interface element with low importance score; according to the method, the interface can be dynamically adjusted so as to adapt to individual requirements of each user.

Description

Technical Field

[0001] This invention relates to the field of interface layout technology, specifically to a method for recommending interface layouts for smart devices. Background Technology

[0002] The interface design of existing smart devices is often based on the needs of average users, lacking truly personalized recommendations that take into account each user's physiological characteristics and usage habits.

[0003] Traditional smart device interfaces typically only offer preset parameter adjustments (such as font size, color contrast, etc.) or fixed layouts, failing to dynamically optimize the interface based on real-time user feedback or behavior. Secondly, many interface design methods still use static layouts, which cannot perceive and dynamically adjust based on user actions (such as click frequency, touch pressure, reaction speed, etc.), thus limiting the improvement of interaction efficiency. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method for recommending interface layouts for smart devices.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: This invention provides a method for recommending interface layouts for smart devices, comprising the following steps: Acquire user behavior data, which includes historical behavior data and real-time operation data. The user behavior data includes the user's click operation coordinates, the type of interaction performed, the duration of each interaction, the type of operation intent of the current task, and the result identifier of the interaction operation. Build a user behavior model based on the user behavior data. The user behavior data is mapped into structured behavior vectors, and the operation behaviors at different time points are integrated. The behavior weight of each behavior record is adjusted according to the time decay factor to construct a user time-series behavior model that reflects the user's current usage habits and preferences. Based on the multidimensional data in the user behavior data, a weighted integral algorithm is used to calculate the importance score of each interface element, and the weight of each dimension is adjusted based on the user profile update strategy. Based on the importance scores of the interface elements, the page controls are reordered and reconstructed, with high-scoring interface elements given priority in the main visual area, and controls with the same score are further sorted according to the historical hot zone priority. Based on users' historical font size usage behavior, adjust the font size of each interface element, increasing the font size of interface elements with high importance scores and decreasing the font size of interface elements with low importance scores; During each interface reordering and reconstruction process, an animation transition mechanism driven by the current change magnitude and the user's historical cognitive load is adopted to achieve a smooth transition in the interface change process.

[0006] As a preferred embodiment of the present invention, the user behavior model is constructed in the following manner: ; Where n represents the number of user operation records; w i The time decay weight for the i-th behavior record is represented as: ; Where λ is a parameter controlling the degree of attenuation of the influence of historical behavior, and T now T is the current system timestamp. i The timestamp of the i-th action record; u i The feature vector representing the i-th operation is denoted as: ; Where, p i The click position is represented by two-dimensional coordinates, t i For operation type, d i a represents the duration of time an element remains in the environment. i For the category of operational intent, r i This is the result of the operation.

[0007] As a preferred embodiment of the present invention, the importance score of the interface element is determined by the following formula: ; Among them, E j Represented as a UI element, S(E) j f represents the importance score of the interface element. click (E j f represents the click frequency of this element. stay (E j f represents the average time a user spends on this element. path (E j f represents the frequency of the element in the user's access path. success (E j f is the success rate of the operation on this element. intent (E j ) represents the intensity index of the operation related to the current interaction intent, and α, β, γ, δ, and ε are the weighting coefficients, respectively.

[0008] As a preferred embodiment of the present invention, the reordering and reconstruction of page controls adopts a multi-objective optimization sorting algorithm based on stability constraints, using the importance score of interface elements as the main order index, and combining historical layout inertia and user familiarity to construct the objective function: ; Among them, V(E) j F(E) represents the objective function score. j The value D(E) represents user familiarity, calculated by weighting the number of times users interact with the control and the duration of their interaction. j ) represents the current position information of the control and the displacement distance in the previous layout, and η1, η2, and η3 are the weight coefficients.

[0009] As a preferred embodiment of the present invention, the reordering and reconstruction of the page controls follows a joint optimization strategy of accessibility and visual focus, and the steps are as follows: All controls are divided into priority zones based on the importance score of the interface elements, including high score zone, medium score zone and low score zone. Distribute controls in high-scoring areas to hot zones; Distribute the controls in the middle scoring area to the secondary hot area; Concentrate controls in the low-scoring areas at the edge.

[0010] As a preferred embodiment of the present invention, the font size adjustment is based on S(E) j The deviation from the mean μ of the scores of all interface elements is amplified by the standard deviation σ, as shown in the following formula: ; Where μ represents the mean score of all interface elements, σ ​​is the standard deviation, and θ is the amplification factor.

[0011] As a preferred embodiment of the present invention, the animation transition mechanism is driven by a cognitive load model, and the animation duration T anim It is determined by the following formula: ; Among them, T0 is the shortest animation duration based on the base, C hist C represents the user's historical average cognitive load. δ This represents the total visual displacement of the controls caused by this rearrangement, where ρ is the response coefficient.

[0012] As a preferred embodiment of the present invention, the interface layout recommendation method further includes the following steps: After the interface adjustment is completed, voice prompts are automatically generated to indicate the changed areas or controls on the interface through voice broadcast. The prompts include the control name and the type of change.

[0013] As a preferred embodiment of the present invention, the voice prompt information is generated using a Top-K change region selection strategy, specifically: Calculate the degree of change of all controls in the calculation interface; Sort and select the n controls with the highest degree of change; Generate voice template prompts for each control.

[0014] The beneficial effects of this invention are: 1. In this invention, by collecting and analyzing user behavior data (such as click frequency, dwell time, operation intent, etc.) in real time, the interface can be dynamically adjusted to adapt to the personalized needs of each user. Unlike traditional interfaces that rely solely on preset adjustments (such as font size, contrast, etc.), this method constructs a user behavior model and combines it with temporal weights to optimize the interface layout in real time, ensuring that the interface design is more in line with the user's operating habits and needs. This dynamic adaptability significantly improves the user's operating efficiency and reduces the occurrence of operational errors.

[0015] 2. In this invention, various methods such as interface rearrangement, font size adjustment, and animation transition are used to ensure smooth interface changes while reducing the cognitive burden on users. For example, interface rearrangement based on user history behavior prioritizes the display of highly important controls, reducing the difficulty for users to find the target function.

[0016] 3. By introducing a user behavior feature model and combining the importance score of controls with a layout optimization algorithm, this invention can optimize the layout order of controls while ensuring interface familiarity. This ensures that important functional areas are presented first in the main visual area of ​​the screen. In addition, by intelligently adjusting the layout and position of controls, the system can dynamically adjust according to the user's operation frequency and habits, thereby improving the accessibility and interaction efficiency of the interface. This method is particularly suitable for user groups, making it more convenient and faster for them to use the interface. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart illustrating the interface layout recommendation method of the present invention. Detailed Implementation

[0018] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0019] like Figure 1As shown, a method for recommending interface layouts for smart devices includes the following steps: Acquire user behavior data, which includes historical behavior data and real-time operation data. The user behavior data includes the user's click operation coordinates, the type of interaction performed, the duration of each interaction, the type of operation intent of the current task, and the result identifier of the interaction operation. Build a user behavior model based on the user behavior data. The user behavior data is mapped into structured behavior vectors, and the operation behaviors at different time points are integrated. The behavior weight of each behavior record is dynamically adjusted according to the time decay factor to construct a user time-series behavior model that reflects the user's current usage habits and preferences. Based on the multidimensional data in the user behavior data, a weighted integral algorithm is used to dynamically calculate the importance score of each interface element, and the weight of each dimension is adaptively adjusted based on the user profile update strategy. Based on the importance scores of the interface elements, the page controls are reordered and reconstructed, with high-scoring interface elements given priority in the main visual area, and controls with the same score are further sorted according to historical hot zone priority, in order to improve the accessibility and visibility of the main functional modules. By combining users' visual preferences and historical font size usage, the font size of each interface element is dynamically adjusted. The font size of interface elements with high importance scores is increased, while the font size of interface elements with low importance scores is decreased, thereby reducing the visual burden on users. During each interface reordering and reconstruction process, an animation transition mechanism driven by the current change magnitude and the user's historical cognitive load is adopted to achieve a smooth transition in the interface change process.

[0020] The core technical solution of this invention is to dynamically adjust the interface display method by collecting user behavior characteristics and interaction data, thereby achieving interface optimization that better meets user needs. Specifically, this method combines various user behavior data, such as click coordinates, interaction type, dwell time, operation intention type, and operation result, and generates a behavior model that reflects user operation habits by analyzing these data. Through this model, this invention can adjust the interface layout in real time according to the user's behavior characteristics to improve the user's operation efficiency and interface understandability.

[0021] It should be noted that in this invention, interface elements and controls refer to the same concept, both referring to visual components or modules that users can interact with in the interface.

[0022] The smart device interface layout recommendation method of the present invention also includes a stable preference control mechanism. The stable preference control mechanism mainly sets a stable preference control field StableMode in the user profile to indicate whether the current user enables the dynamic adjustment function of the interface. This field is configured by the system initialization and allows the user to manually adjust it in the system settings.

[0023] Its specific working mechanism includes: How to set the StableMode field: StableMode is a boolean value. A value of True indicates that the user has enabled the stable preference mode and disabled dynamic interface reconstruction. A value of False indicates that dynamic interface adjustments are allowed based on the user behavior model. The default initial configuration of StableMode is True.

[0024] Interface reconstruction trigger condition control: When StableMode=True, the system completes the importance score of interface elements based on the user behavior model, but does not directly trigger the reordering of controls or adjustment of font size. It only records and caches the recommendation results. When the user explicitly selects "Enable Smart Optimized Recommendation" in the settings interface, StableMode is set to False, and the system dynamically updates the interface layout based on the behavior model.

[0025] Guidance and prompting mechanism: When the system first suggests that a user enable the dynamic recommendation function, it clearly informs the user through the interface that the operation may cause interface changes and reminds the user that the function can be turned off at any time. Before each layout change operation, the system uses a change magnitude judgment mechanism based on the user's historical cognitive vector. Only when the change magnitude exceeds a preset threshold will the animated transition interface adjustment be triggered, and voice or visual prompts will be given for the adjusted content.

[0026] In this process, the aforementioned stable preference control mechanism works in conjunction with the interface reordering mechanism and animation transition mechanism to ensure that the interface recommendation is both intelligent and takes into account the user's need for information stability, achieving the goal of "user controllability + system intelligence".

[0027] Furthermore, the user behavior model is constructed as follows: ; Where n represents the number of user operation records; w i The time decay weight for the i-th behavior record is represented as: ; Where λ is a parameter factor that controls the degree of decay of the influence of historical behavior, and is a positive number, Tnow T is the current system timestamp. i The timestamp of the i-th action record; u i The feature vector representing the i-th operation is denoted as: ; Where, p i The click position is represented by two-dimensional coordinates, t i For the operation type (e.g., click, swipe, long press, etc.), d i The duration of time an element is displayed reflects the allocation of user attention. i For operation intent categories (such as search, confirmation, input, etc.), inference is made through task context and sequence modeling, r i The result of this operation is recorded as 1 for success and 0 for failure.

[0028] This formula is designed to address two core technical challenges in user behavior modeling: Dynamic issues: User interaction behavior changes over time, and the value of early behavior for current interface optimization gradually decreases; Multi-dimensional behavior integration issues: A single dimension (such as the number of clicks) is insufficient to reflect the user's true usage habits. Location, duration, intent, and operation success rate must be considered comprehensively.

[0029] By introducing w i This allows the model to balance the influence of recent and historical behavior. For example, if a user frequently clicked a button last week but hardly used it this week, the importance of that button will naturally decrease over time.

[0030] This user behavior model constructs a comprehensive behavioral model that reflects user operating habits and preferences by analyzing historical behavior data and real-time operation data. The use of λ to dynamically adjust the behavior weights is because user behavior changes over time. In particular, for users, not performing a certain operation for a long time may cause the impact of that behavior to gradually decrease. Therefore, using a time decay method can better reflect the user's current behavioral habits.

[0031] During operation, the front-end data collection SDK first obtains the following interaction data in real time through DOM-bound events: click location represented by two-dimensional coordinates, operation type, element dwell time, operation intent, and operation result. The data is structured into behavior logs, with each log entry corresponding to the aforementioned feature vector u. i ; For each log entry, the decay weight is calculated based on the time difference between the current time and the behavior record. Preferably, the value of λ is in the range of [0.001, 0.05]. If λ is too large, the system will rely too much on recent behavior; if it is too small, it will rely too much on historical behavior. For mobile interactive interfaces, λ=0.02 is more balanced and can effectively reflect the decay trend of user behavior over the past week. Ultimately, model H represents a multi-dimensional weighted average behavioral state: If a user has been frequently clicking on a certain control recently, then p i The distribution of these organisms is concentrated in this area; If users frequently use "confirm" type interactions, then a i The probability distribution is biased towards "confirmation"; Duration d i A higher number of elements indicates higher user attention.

[0032] Model H serves as the input for subsequent layout rearrangement and font size adjustment.

[0033] Furthermore, the importance score of the interface element is determined by the following formula: ; Among them, E j Represented as a UI element, S(E) j f represents the importance score of the interface element. click (E j The click frequency (E) represents the activity level of this element, indicating its engagement with users. It is calculated by counting the number of clicks made by users within a specific time window (e.g., 7 days or 30 days). j The number of times and normalized to a frequency value; f stay (E j This represents the average time a user spends on this element, reflecting the user's level of attention. The calculation method is: take E... j The average and normalized value of all interaction dwell times; f path (E j The frequency of this element in the user's access path represents its criticality in the task flow. The calculation method is to statistically analyze E from the task behavior sequence. j Frequency of occurrence (i.e., the number of times it appears in the task path); f success (E j The success rate of this element's operation is used to evaluate its ease of use. It is calculated as the ratio of the number of successful attempts to the total number of attempts. f intent (E j(I) is an operation intensity metric related to the current interaction intent, used to measure its contextual relevance. The current task intent I is extracted through the model. t Based on historical data analysis, this control E j with I t The relevance is expressed as follows: ; in, Indicates control E j Intent I t The conditional probability of being used; α, β, γ, δ, and ε are weight coefficients respectively, and satisfy α+β+γ+δ+ε=1.

[0034] α (click frequency weight): The recommended range is [0.2, 0.35]. Clicks are a significant indicator of behavior and should be given a medium to high weight. β (Dwell Time Weight): Recommended value is [0.1, 0.25], as its weight is slightly lower due to its influence on differences in user reading speed; γ (Path Frequency Weight): It is recommended to set it in [0.15, 0.3] to reflect the role of the control in completing the task; δ (Success Rate Weight): It is recommended to set it to [0.1, 0.2] to filter out low-quality controls; ε (Intent Matching Weight): Should be dynamically adjusted. When the intent recognition accuracy is high, a high value [0.2, 0.35] can be set to enhance the system's adaptability.

[0035] Recommended initial default values ​​are as follows (for general users): α=0.25 (click frequency is dominant), β=0.20, γ=0.20, δ=0.15, ε=0.20.

[0036] For example: If a user repeatedly clicks on "Service Guide" but the success rate is low, the system can adjust the f... intent with f success This significantly elevates the control's position and adds a tooltip animation to reduce accidental operation.

[0037] By weighting and integrating multiple dimensions (click frequency, dwell time, access path frequency, operation success rate, and operation intent intensity), a comprehensive importance score for each interface element is obtained. The weighted integration algorithm is used because different dimensions of behavioral characteristics have different impacts on users' operating habits and interface experience. For example, elements with high click frequency indicate that users have a strong demand for those elements, while elements with low operation success rates may need to be adjusted to improve user experience. In this way, the importance of each interface element can be accurately assessed, thereby enabling reasonable layout optimization.

[0038] It should be noted that in actual use, controls may sometimes be mistakenly judged as "ignorable" elements due to low interaction frequency. In order to further enhance the executability and intuitiveness of users' key tasks, especially for users with declining cognitive or visual abilities, a semantic importance index has been added to the original importance score of interface elements. This index is used to introduce semantic priority factors, that is, to judge the importance of semantics.

[0039] The formula for modeling the semantic importance index is as follows: ; Among them, I sem (E j ) is control E j The semantic importance index has a value range of [0,1]. f role (E j `f` is a function for defining the role level of a control in the task flow (the recommended value range is 0-1, with roles such as main task buttons ("Submit", "Confirm", "Next", etc.) being 1, and auxiliary setting buttons ("Language Settings", "Theme Color", etc.) being 0.2). This control role level function `f`... role (E j Modeling can be performed by pre-configuring a table of suggested values ​​for each control; f task (E j ) is the control task coverage function, which represents the degree to which the control covers or supports the task objective. Similarly, it can be modeled by pre-configuring a table of suggested values ​​for each control. For example, the suggested scores for controls such as "medication reminder", "heart rate monitoring" and "emergency contact" are 0.8~0.9, while controls that are weakly associated with the task objective, such as "night mode switch", are 0.1~0.2. f critical (E j ) is a key function for determining the function of the control, and it is a Boolean function. If E j This is a core system function; its value is 1 if it is not a core function, and 0 otherwise.

[0040] ω1 is the semantic importance index weight factor, ω2 is the control task coverage weight factor, and ω3 is the control key function judgment weight factor, and they satisfy the constraint condition: ω1+ω2+ω3=1. The initial values ​​of each weight factor are set as follows: ω1=0.4, emphasizing the task responsibility position of the control; ω2=0.4, highlighting the coupling strength between the control and the task goal; and ω3=0.2, as a Boolean enhancement term.

[0041] The semantic importance index modeling result I sem (E j This will be compared with the importance score of interface elements, S(E).j Together with the "font size adjustment module", they form a two-dimensional control mechanism, thereby ensuring that low-frequency but semantically critical controls can obtain appropriate font size display.

[0042] Therefore, before using the standard deviation amplification mechanism to obtain the basis for font size adjustment, it is necessary to first determine whether the control is a high-level semantic importance indicator. For this purpose, a threshold I is set. max When the semantic importance index modeling result I sem (E j () greater than threshold I max When this happens, the system directly assigns the maximum font size to the control to ensure visibility. Optionally, I max It is recommended to set the range to 0.6~0.7 to ensure that only controls with high semantic criticality enter the priority channel.

[0043] For example, in user health management applications, there are controls such as "medication reminders," "heart rate monitoring," and "emergency contacts." These controls are not frequently used in daily life, but they are crucial in critical moments. When calculating the importance score of interface elements, the "heart rate monitoring" control, having only been interacted with once in the past 7 days, results in a low S(E) score. j The score was low; However, semantic importance metrics are used to model and evaluate f in this control. role (E j = 0.9 (Main Responsibility Control), f task (E j ) = 0.85 (core task node), f critical (E j )=1 (system-level critical), with weighting factors ω1=0.4, ω2=0.4, and ω3=0.2 respectively, then: I sem (E j The final calculation result is 0.9, which is much higher than I. max It is recommended to set the range to 0.6~0.7 (preferably 0.65), therefore, the system directly assigns the maximum font size to this control.

[0044] Taking the "medication reminder" control in a user health management application as an example, although its daily interaction frequency is not high, it has a direct impact on the user's health tasks. In traditional layout optimization, this type of control is misjudged as secondary information due to its low frequency, resulting in smaller font size and reduced recognizability. This invention identifies the key attributes of the control through semantic importance indicators and ensures that it is displayed at the maximum font size in the interface. This enables users to quickly complete the identification and response of key information with low visual cognitive load, significantly improving the overall interactive experience.

[0045] Furthermore, the reordering and reconstruction of page controls employs a multi-objective optimization sorting algorithm based on stability constraints, using the importance score of interface elements as the primary ordering indicator, and combining historical layout inertia and user familiarity to construct the objective function: ; Among them, V(E) j F(E) represents the objective function score. j The number N represents user familiarity, measured by the number of times the user interacts with the control. j With stay time T j The weighted average yields the following formula: ; in, It is expressed as the sum of the weighted products of the number of interactions and dwell time of all controls, i.e., the standardized denominator, ensuring that each F(E) is equal to the sum of the weighted products of the number of interactions and dwell time of all controls. j Normalize to the interval [0,1]; D(E j The formula () represents the distance between the current position of the control and its displacement in the previous layout. ; Among them, (x j (t) ,y j (t) (x) represents the current coordinates of the control. j (t-1) ,y j (t-1) () represents the coordinates of the previous layout; η1, η2, and η3 are weighting coefficients, respectively. η1 controls the degree of importance attached to the current interaction, η2 controls the maintenance of user familiarity to prevent frequent reordering from causing cognitive burden, and η3 controls the maintenance of interface stability (minimizing disturbance) to avoid large-scale control migration from affecting interface stability.

[0046] Alternatively, the recommended parameter settings are as follows (adjustable adaptively): η1∈[0.4,0.6], which prioritizes reflecting the importance of controls; η2∈[0.2,0.4], moderately preserving user habits; η3∈[0.1,0.3], appropriately reduce interface jumps; These coefficients are designed based on the principles of prioritizing main functions, protecting usage memory, and ensuring a stable interactive experience.

[0047] This algorithm is based on a multi-objective optimization strategy with stability constraints, aiming to maximize user experience and ease of use of the interface. By comprehensively considering the importance score of controls, user familiarity, and layout inertia, it sorts and optimizes interface controls to ensure that important elements are displayed first, while minimizing the user's adaptation cost to interface changes.

[0048] During operation, the S(E) corresponding to the control is first collected. j ), accumulate the number of user interactions with the control and the average dwell time, and calculate F(E) j ), and calculate the displacement distance D(E) between the current position and the previous layout. j ); For each control E j Calculate its objective function score V(E) j Then sort the controls from highest to lowest according to their objective function scores; Based on the sorting results, try to place the control in the hot zone, the secondary hot zone, and the edge area in turn. If the pre-allocated position is occupied, start the local exchange search mechanism and try to make a small-scale exchange in the neighboring area to satisfy the local optimum. If the D(E) of a certain control j )>D max (Perturbation threshold, recommended value: D) max If the value is 30 pixels, then it will be forced to remain in its original position to avoid frequent and drastic layout changes in a short period of time (a cooldown time can be set, such as allowing only one reflow within 60 seconds).

[0049] Furthermore, the reordering and reconstruction of the page controls follows a joint optimization strategy of accessibility and visual focus, with the following steps: All controls were divided into priority zones based on their importance scores, including the high-score zone (S(E)). j )≥μ+σ), intermediate partition (μ-σ<S(E) j )<μ+σ)and low-scoring partitions (S(E) j )≤μ-σ), where μ is the sum of all controls S(E) j The average value of ) and σ is the standard deviation. The design of this partitioning strategy is based on the discrete distribution characteristics of the standard normal distribution in statistics. It ensures that high-priority controls are significantly higher than the average level, which helps to clarify the partition boundaries and facilitates interface mapping. Distribute controls in high-scoring areas to hot zones (such as the center of the interface or the bottom thumb-accessible area). Distribute the controls in the middle scoring area to the secondary hot zone (near the edge of the hot zone, an area that can be quickly swiped to reach the target); Concentrate controls in low-scoring areas in the edge areas (less interactive areas, such as the top corners and hidden menus).

[0050] By prioritizing the scores of interface elements and placing high-priority elements in users' hot zones, we can improve the ease of use of the interface and the accessibility of important functions.

[0051] Furthermore, in existing smart device interface designs, users often require larger fonts to ensure readability due to physiological characteristics such as decreased vision and increased cognitive load. However, traditional interface font size design often uses a fixed size or is based solely on overall scaling, failing to personalize and dynamically adjust according to the different levels of attention users pay to various interface elements in different interaction scenarios. This results in problems such as unclear information hierarchy, lack of differentiation between important and secondary information, and redundant interface space usage, reducing user interaction efficiency and comfort. To address the aforementioned technical challenges, this invention proposes a dynamic font size adjustment mechanism based on element importance scores. This mechanism can ensure that key information is clear and easy to read while compressing the visual space occupied by non-key information, thereby achieving efficient allocation of visual resources and effectively improving the overall accessibility and readability of the interface.

[0052] The font size adjustment is based on S(E) j The deviation from the mean μ of the scores of all interface elements is amplified by the standard deviation σ, as shown in the following formula: ; Where μ represents the mean score of all interface elements, serving as the baseline font size; σ is the standard deviation, and the larger the standard deviation, the greater the difference in the distribution of element importance, and the greater the adjustment range of the font size; θ is the amplification factor, used to control the amplification effect of deviation on the font size and prevent excessive amplification or reduction. If the user group generally has a serious decline in vision, a larger value (such as 2.0~2.5) can be selected to significantly enhance the readability of prominent content; if the hierarchy of interface content is not obvious, a medium value (such as 1.5~2.0) can be selected; if the interface is already relatively simple, a smaller value (such as 1.0~1.5) can be selected to prevent excessive visual burden. Deviation This indicates the relative importance of the element with respect to the whole; a positive deviation corresponds to increasing the font size, and a negative deviation corresponds to decreasing the font size.

[0053] This formula introduces normalized deviation amplification based on existing technology. It can linearly amplify or compress the font size according to the degree of deviation of the element score from the overall mean, realizing a dynamic allocation of increasing the font size of significant content and decreasing the font size of non-core content. Moreover, the font size adjustment range is strictly controlled within the preset upper and lower limits [F]. min ,F max ].

[0054] The core of this mechanism is to ensure that important content is enlarged to improve its readability, while the font size of unimportant elements is appropriately compressed to free up more visual space. The purpose of this design is to solve the visual burden on users, especially considering the vision problems of many users. By dynamically adjusting the font size, it makes the visual experience more comfortable and easier to understand.

[0055] Furthermore, in traditional smart device interface systems, interface adjustments (such as layout rearrangement, control position movement, or size change) typically employ instant refresh or fixed-duration transition animations. This presents two significant problems: users are highly sensitive to dynamic changes in the interface, and if the animation duration cannot be flexibly adapted to the complexity of the current interface adjustment and historical operational load, it may lead to distraction, anxiety, and delayed understanding; and existing methods are mostly static animation solutions (such as uniformly setting a duration of 300ms), which cannot comprehensively consider the magnitude of interface changes (control displacement, size adjustment) and the user's previous familiarity with interface dynamics and cognitive adaptability. To address the aforementioned issues, this invention proposes a cognitive load-driven dynamic animation transition mechanism that can adjust the animation duration and transition smoothness as needed based on the user's historical operational load and the current interface change magnitude, thereby maximizing the user-friendliness and naturalness of interface adjustments. This invention implements an interface animation transition mechanism through the following core steps: First, collect users' historical cognitive load data, including average dwell time (reflecting comprehension speed), operation error rate (reflecting acceptance level), and dwell time during the last interface redesign. Secondly, calculate the total visual displacement caused by this interface rearrangement: sum the displacement distances of all adjusted controls to quantitatively reflect the magnitude of the change; Furthermore, the animation transition mechanism is driven by a cognitive load model, with an animation duration T. anim It is determined by the following formula: ; Among them, T0 is the minimum animation duration based on the base (optionally, T0 = 300~500ms), to avoid visual jumps caused by excessively short durations. hist C represents the average historical cognitive load of users, reflecting the comprehension pressure experienced by users over long-term interactions. It is defined as the normalized combination of the average time a user spends on the interface across several historical operations and the error rate. δ This represents the total visual displacement of controls caused by this rearrangement. The unit can be defined as pixels or normalized relative displacement, with the weighted average of the two taken as the median. This further enhances the smoothness for extreme values ​​(such as an abnormally high value). ρ is the response coefficient, used to control the amplification effect of the change amplitude and cognitive load on the animation duration, ensuring that the animation is slow and the changes are natural under high cognitive load. Recommended value: ρ = 500~800ms. If the load is moderate (C...hist +C δ ≈1), the animation length increases by about 250~400ms, and the length increases by more than 800ms under high load.

[0056] Specifically, the user's historical average cognitive load C hist The calculation method is as follows: ; in, T is expressed as the historical average dwell time (seconds). ref E is the reference time (10s recommended). rate λ represents the historical error rate (0~1). err λ is the error rate weighting coefficient, preferably... err It is 0.5.

[0057] The total visual displacement of controls caused by this rearrangement, C δ The calculation method is as follows: ; If the historical load is high (C) hist →1), but the change this time is small (C) δ →0), the animation still needs to be lengthened to maintain cognitive safety. If the change is drastic and the historical adaptability is good, the animation length will continue to increase with the change. When both are high, the animation will slow down significantly. Finally, an animation transition based on progressive interpolation is executed. Throughout the entire animation execution cycle, non-linear interpolation (such as ease-in-out curves) is used to ensure visual smoothness and reduce abruptness.

[0058] The animation transition mechanism is driven by a cognitive load model. It achieves a smooth transition of interface changes by dynamically adjusting the duration of the animation. The higher the user's cognitive load, the slower the interface change should be to reduce visual fatigue caused by interface adjustments. This mechanism aims to improve the user's interface experience and avoid abrupt interface changes from causing inconvenience to the user.

[0059] For example, in the interface adjustment process of this invention, the animation transition mechanism performs the following operations in sequence: Collect historical data: The system analyzes the average dwell time and error rate of the user's last 20 operations; Analyze this layout adjustment: Calculate the displacement of all controls and generate C. δ ; Calculate the animation duration using the formula: Substitute: T0=400ms, ρ=600ms Assumption: C hist =0.8,C δ =0.6 but: ; Set animation parameters: Animation interpolation function: ease-in-out (smooth curve), animation duration: 820ms; Perform control animation: The position and size of the control change gradually, and the interface prompts and voice broadcasts are triggered simultaneously.

[0060] Furthermore, the interface layout recommendation method also includes the following steps: After the interface adjustment is completed, voice prompts are automatically generated to point out the changed areas or controls in the interface through voice broadcast. The prompts include the control name and the type of change. The voice prompt information is generated using a Top-K change region selection strategy, specifically: The degree of change of all controls in the calculation interface, including weighted scores for changes in position, size, color, or function; Sort and select the n controls with the highest degree of change; Generate voice template prompts for each control.

[0061] The voice prompt generation scheme adopts a Top-K change area selection strategy to help users more easily understand interface changes. By calculating the degree of control changes and generating voice prompts for controls with significant changes, users can quickly know which interface elements have changed. This is especially important for users, as they may have difficulty visually identifying changes in the interface.

[0062] It should be noted that although existing smart devices are quite widespread, users sometimes use low-end models with weak processing power and limited memory (typically less than 3GB of RAM and a CPU clock speed not exceeding 1.5GHz). To balance the intelligence of the interface layout reconstruction with the stability of system operation, this method presets two schemes in the system architecture: a standard UI template and a lightweight UI template. It also determines whether the current operating environment is a low-end model. If the user is using a low-end model with weak processing power and limited memory, then: Lightweight UI templates reduce CPU and memory load by minimizing animation elements, compressing image resources, and simplifying control styles. Low-end models load a lightweight UI template by default upon startup, retaining only the logic for reordering core control elements and adjusting font size; Score of interface elements S(E) j The layout optimization and sorting process can still be carried out in low-resource mode, but the result is reflected in the visual presentation as low-frequency reconstruction to avoid frequent changes; Furthermore, when the runtime environment is a lightweight UI template, a static switching method is used for presentation.

[0063] By setting up both standard and lightweight UI templates, the layout optimization method remains feasible even with limited device resources, without affecting the overall stable operation of the system. Combined with the stable preference control mechanism, it is more suitable for users' daily use.

[0064] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for recommending interface layouts for smart devices, characterized in that, Includes the following steps: Acquire user behavior data, which includes historical behavior data and real-time operation data. The user behavior data includes the user's click operation coordinates, the type of interaction performed, the duration of each interaction, the type of operation intent of the current task, and the result identifier of the interaction operation. Build a user behavior model based on the user behavior data. The user behavior data is mapped into structured behavior vectors, and the operation behaviors at different time points are integrated. The behavior weight of each behavior record is adjusted according to the time decay factor to construct a user time-series behavior model that reflects the user's current usage habits and preferences. Based on the multidimensional data in the user behavior data, a weighted integral algorithm is used to calculate the importance score of each interface element, and the weight of each dimension is adjusted based on the user profile update strategy. Based on the importance scores of the interface elements, the page controls are reordered and reconstructed, with high-scoring interface elements given priority in the main visual area, and controls with the same score are further sorted according to the historical hot zone priority. Based on users' historical font size usage behavior, adjust the font size of each interface element, increasing the font size of interface elements with high importance scores and decreasing the font size of interface elements with low importance scores; During each interface reordering and reconstruction process, an animation transition mechanism driven by the current change magnitude and the user's historical cognitive load is adopted to achieve a smooth transition in the interface change process.

2. The interface layout recommendation method for smart devices according to claim 1, characterized in that, The user behavior model is constructed as follows: ； Where n represents the number of user operation records; w i The time decay weight for the i-th behavior record is represented as: ； Where λ is a parameter controlling the degree of attenuation of the influence of historical behavior, and T now T is the current system timestamp. i The timestamp of the i-th action record; u i The feature vector representing the i-th operation is denoted as: ； Where, p i The click position is represented by two-dimensional coordinates, t i For operation type, d i a represents the duration of time an element remains in the environment. i For the category of operational intent, r i This is the result of the operation.

3. The interface layout recommendation method for smart devices according to claim 2, characterized in that, The importance score of the interface element is determined by the following formula: ； Among them, E j Represented as a UI element, S(E) j f represents the importance score of the interface element. click (E j f represents the click frequency of this element. stay (E j f represents the average time a user spends on this element. path (E j f represents the frequency of the element in the user's access path. success (E j f is the success rate of the operation on this element. intent (E j ) represents the intensity index of the operation related to the current interaction intent, and α, β, γ, δ, and ε are the weighting coefficients, respectively.

4. The interface layout recommendation method for smart devices according to claim 3, characterized in that, The reordering and reconstruction of page controls adopts a multi-objective optimization sorting algorithm based on stability constraints. The algorithm uses the importance score of interface elements as the main order index and combines historical layout inertia and user familiarity to construct the objective function. ； Among them, V(E) j F(E) represents the score of the objective function. j The value D(E) represents user familiarity, calculated by weighting the number of times users interact with the control and the duration of their interaction. j ) represents the current position information of the control and the displacement distance in the previous layout, and η1, η2, and η3 are the weight coefficients.

5. The interface layout recommendation method for smart devices according to claim 4, characterized in that, The reordering and reconstruction of page controls follows a joint optimization strategy of accessibility and visual focus, and the steps are as follows: All controls are divided into priority zones based on the importance score of the interface elements, including high score zone, medium score zone and low score zone. Distribute controls in high-scoring areas to hot zones; Distribute the controls in the middle scoring area to the secondary hot zone; Concentrate controls in the low-scoring areas at the edge.

6. The interface layout recommendation method for smart devices according to claim 3, characterized in that, The font size adjustment is based on S(E) j The deviation from the mean μ of the scores of all interface elements is amplified by the standard deviation σ, as shown in the following formula: ； Where μ represents the mean score of all interface elements, σ ​​is the standard deviation, and θ is the amplification factor.

7. The interface layout recommendation method for smart devices according to claim 1, characterized in that, The animation transition mechanism is driven by a cognitive load model, with an animation duration T. anim It is determined by the following formula: ； Among them, T0 is the shortest animation duration based on the base, C hist C represents the user's historical average cognitive load. δ This represents the total visual displacement of the controls caused by this rearrangement, where ρ is the response coefficient.

8. The interface layout recommendation method for smart devices according to claim 1, characterized in that, The interface layout recommendation method also includes the following steps: After the interface adjustment is completed, voice prompts are automatically generated to indicate the changed areas or controls on the interface through voice broadcast. The prompts include the control name and the type of change.

9. The interface layout recommendation method for smart devices according to claim 8, characterized in that, The voice prompt information is generated using a Top-K change region selection strategy, specifically: Calculate the degree of change of all controls in the calculation interface; Sort and select the n controls with the highest degree of change; Generate voice template prompts for each control.

Images