A quick navigation control method and system for mobile terminal software

Abstract

This invention relates to the field of navigation control technology and discloses a fast navigation control method and system for mobile software. The method includes: acquiring click events and timestamps, preprocessing them to obtain an operation sequence dataset; extracting high-frequency click intervals and function switching patterns to determine a first rhythm vector; judging high-frequency operation scenarios to obtain a predicted navigation demand sequence; adjusting the sorting of navigation options and incorporating haptic feedback patterns to obtain an option layout configuration; matching and filtering the option layout configuration with a second rhythm vector in the current scenario to obtain an option subset and calculating trigger time nodes to determine timing parameters; adjusting the display priority of the option subset to generate a synchronous haptic feedback sequence to obtain the final response interface; acquiring the user click time interval sequence and updating the predicted navigation demand sequence to obtain the final navigation path sequence. This method can achieve real-time adaptation of the navigation interface to user operating habits, improving the accuracy of navigation effects.

Description

Technical Field

[0001] This invention relates to the field of navigation control technology, and in particular to a fast navigation control method and system for mobile terminal software. Background Technology

[0002] With the rapid development of mobile internet technology, smartphones and various mobile applications have become essential tools for users' daily work and life. Navigation control in mobile software, as a core aspect of human-computer interaction, directly determines the efficiency and experience of user operations. A high-quality navigation system needs to quickly respond to user needs in diverse scenarios, helping users efficiently complete operations such as function switching and information retrieval through an intuitive interface layout and smooth interaction logic. Therefore, achieving intelligent and adaptive navigation control has become a key direction for enhancing the competitiveness of mobile applications.

[0003] Current mobile software navigation control methods are mostly based on preset interface layouts and fixed interaction logic, providing navigation options through static menus, fixed-position buttons, and other means. On the one hand, different users have significantly different operating rhythms; some users tend to click frequently and quickly, while others prefer to browse slowly. Existing fixed navigation layouts cannot adjust option priorities accordingly. On the other hand, users' operational needs also change dynamically in different scenarios. In high-frequency operation scenarios, users need to quickly switch core functions, but existing technologies lack in-depth analysis of real-time operation data and cannot capture users' dynamic needs. This forces users to click or swipe multiple times to find the target option, increasing operational costs and response latency.

[0004] In summary, existing technologies struggle to dynamically adjust navigation options by accurately analyzing the frequency and rhythm of user operations, resulting in low navigation response accuracy. Summary of the Invention

[0005] This invention provides a fast navigation control method and system for mobile software, which can dynamically generate navigation option layouts that adapt to the user's operation rhythm and scenario needs by accurately analyzing real-time changes in user operations, thereby improving the accuracy and real-time performance of navigation response.

[0006] In a first aspect, to solve the above-mentioned technical problems, the present invention provides a fast navigation control method for mobile terminal software, comprising:

[0007] The user's click events and corresponding timestamp data during the interaction process are obtained, preprocessed, and the operation sequence dataset is obtained.

[0008] Based on the operation sequence dataset, high-frequency click intervals and function switching patterns are extracted to determine the first rhythm vector of user operations.

[0009] Based on the first rhythm vector, a support vector machine algorithm is used to determine high-frequency operation scenarios. The high-frequency operation scenarios are matched with a preset navigation demand mapping table to obtain a predicted navigation demand sequence.

[0010] Based on the predicted navigation demand sequence, the display order of navigation options is adjusted to obtain a preliminary interface layout, and the option layout configuration is obtained by matching the preliminary interface layout with the preset haptic feedback mapping relationship.

[0011] Obtain the user's second rhythm vector in the current scenario, match and filter the option layout configuration with the second rhythm vector to obtain an option subset, calculate the trigger time node of the option subset based on the high-frequency click interval, and determine the timing parameters of the second rhythm vector;

[0012] Based on the second rhythm vector and the timing parameter, the user's current interface state is obtained, the display priority of the option subset is adjusted, and a synchronized haptic feedback sequence is generated. The current interface state is optimized based on the display priority and the haptic feedback sequence to obtain the final response interface.

[0013] Based on the final response interface, the time interval sequence of the click event is obtained, the predicted navigation demand sequence is updated based on the time interval sequence, and navigation path features adapted to the current scene are extracted to obtain the final navigation path sequence.

[0014] Preferably, the step of acquiring user click events and corresponding timestamp data during the interaction process, and preprocessing them to obtain an operation sequence dataset includes:

[0015] The user's click events during the interaction process are obtained and recorded according to the corresponding timestamp data to obtain an initial dataset;

[0016] For the initial dataset, the time interval between every two adjacent click events is calculated. If the time interval is less than a preset time interval threshold, the latter of the two adjacent click events is determined to be an abnormal click, and the abnormal click is removed to obtain a filtering operation sequence.

[0017] Based on the filtering operation sequence, by analyzing the frequency and time distribution of the click events, the user operation behavior pattern is extracted to obtain a behavior feature dataset.

[0018] The clustering center points of the behavioral feature dataset are calculated iteratively using a clustering algorithm. Based on the clustering center points, the behavioral feature dataset is classified to obtain the operation sequence dataset.

[0019] Preferably, the step of extracting high-frequency click intervals and function switching patterns from the operation sequence dataset to determine the first rhythm vector of user operations includes:

[0020] The operation sequence dataset is segmented by a preset time window, and the time distribution features are extracted to obtain the initial behavior state sequence;

[0021] For the initial behavioral state sequence, a hidden Markov model is used to calculate the state transition probability between adjacent behavioral states, and the state transition process with the state transition probability higher than a preset probability threshold is determined as the function switching rule.

[0022] Calculate the time difference between adjacent clicks in the initial behavior state sequence. If the time difference meets the preset high-frequency click interval range within the preset number of consecutive click intervals, then the time difference within the preset high-frequency click interval range is classified as the high-frequency click interval.

[0023] The high-frequency click interval and the function switching pattern are fused with the time distribution characteristics to obtain the first rhythm vector.

[0024] Preferably, the step of determining high-frequency operation scenarios based on the first rhythm vector using a support vector machine algorithm, and matching the high-frequency operation scenarios with a preset navigation demand mapping table to obtain a predicted navigation demand sequence includes:

[0025] When the average value of the high-frequency click interval is less than the preset click interval threshold, the state transition probability of adjacent click events in the high-frequency click interval is extracted according to the first rhythm vector.

[0026] The classification boundary features are determined by the support vector machine algorithm. The high-frequency operation scenarios are then selected from the first rhythm vector by combining the classification boundary features and the state transition probabilities.

[0027] The high-frequency operation scenarios are matched with a preset navigation demand mapping table to obtain the user's potential needs. The potential needs are then arranged in the order of user operation time to obtain the predicted navigation demand sequence.

[0028] Preferably, the step of adjusting the display order of navigation options according to the predicted navigation demand sequence to obtain a preliminary interface layout, and matching the preliminary interface layout with a preset haptic feedback mapping relationship to obtain an option layout configuration, includes:

[0029] Based on the predicted navigation demand sequence, the frequency of occurrence and operation completion time of each navigation demand are extracted, and the priority weight of each navigation option is calculated based on the frequency of occurrence and the operation completion time.

[0030] According to the priority weights from high to low, the display order of the corresponding navigation options is arranged in descending order, and the interface is rendered to obtain the preliminary interface layout.

[0031] Obtain the functional attributes of each layout element in the initial interface layout, and match the corresponding haptic feedback parameters for each navigation option based on the priority weight and the functional attributes and the preset haptic feedback mapping relationship.

[0032] The initial interface layout is associated and integrated with the haptic feedback parameters to generate an option layout configuration that includes display sorting strategy and haptic feedback strategy.

[0033] Preferably, the step of obtaining the user's second rhythm vector in the current scenario, matching and filtering the option layout configuration with the second rhythm vector to obtain an option subset, calculating the trigger time node of the option subset based on the high-frequency click interval, and determining the timing parameters of the second rhythm vector includes:

[0034] Obtain the real-time click events and timestamps of the user's current operation, and generate the second rhythm vector;

[0035] Calculate the distance between the second rhythm vector and the classification boundary feature, normalize the distance, and obtain the matching degree between the second rhythm vector and the option layout configuration;

[0036] When the matching degree is higher than the preset matching degree threshold, the option layout configuration is filtered by the preset function switching simplification rules to obtain the option subset;

[0037] Based on the high-frequency click interval in the second rhythm vector, and combined with the haptic feedback parameters, the trigger time nodes of each navigation option in the option subset are calculated, and the duration between the initial trigger node and the last trigger node is determined as the timing parameter.

[0038] Preferably, the step of obtaining the user's current interface state based on the second rhythm vector and the timing parameter, adjusting the display priority of the option subset, generating a synchronized haptic feedback sequence, and optimizing the current interface state based on the display priority and the haptic feedback sequence to obtain the final response interface includes:

[0039] If the timing parameter is greater than a preset time threshold, then when the next click event of the user operation is triggered, the user's current interface state is obtained;

[0040] Based on the current interface state and in conjunction with the second rhythm vector, the display priority of the option subset is adjusted to obtain the adjusted option subset;

[0041] Based on the adjusted option subset, the current interface state is rendered to obtain a response interface. Through a preset haptic feedback mapping relationship, a haptic feedback sequence synchronized with the response interface is generated.

[0042] The adjusted option subset and the haptic feedback sequence are injected into the response interface to obtain the final response interface.

[0043] Secondly, the present invention provides a fast navigation control system for mobile terminal software, comprising:

[0044] The data preprocessing module is used to acquire user click events and corresponding timestamp data during the interaction process, perform preprocessing, and obtain an operation sequence dataset;

[0045] The rhythm vector generation module is used to extract high-frequency click intervals and function switching patterns based on the operation sequence dataset to determine the first rhythm vector of the user operation;

[0046] The navigation demand prediction module is used to determine high-frequency operation scenarios based on the first rhythm vector using a support vector machine algorithm, and to obtain a predicted navigation demand sequence by matching the high-frequency operation scenarios with a preset navigation demand mapping table.

[0047] The layout configuration generation module is used to adjust the display order of navigation options according to the predicted navigation demand sequence to obtain a preliminary interface layout, and to match the preliminary interface layout with a preset haptic feedback mapping relationship to obtain the option layout configuration.

[0048] The timing parameter determination module is used to obtain the user's second rhythm vector in the current scenario, match and filter the option layout configuration with the second rhythm vector to obtain an option subset, calculate the trigger time node of the option subset based on the high-frequency click interval, and determine the timing parameter of the second rhythm vector.

[0049] The response interface optimization module is used to obtain the user's current interface state based on the second rhythm vector and the timing parameter, adjust the display priority of the option subset, generate a synchronized haptic feedback sequence, optimize the current interface state based on the display priority and the haptic feedback sequence, and obtain the final response interface.

[0050] The navigation path update module is used to obtain the time interval sequence of the click event based on the final response interface, update the predicted navigation demand sequence based on the time interval sequence, and extract navigation path features adapted to the current scene to obtain the final navigation path sequence.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] (1) This invention obtains the operation sequence dataset by acquiring click events and corresponding timestamp data during user interaction, and then extracts high-frequency click intervals and function switching patterns to determine the first rhythm vector. This process can comprehensively capture the dynamic characteristics of user operations, transforming scattered interaction data into structured rhythm vectors, enabling the system to accurately perceive the user's operating habits and real-time status, providing a data basis for subsequent navigation adjustments, thereby improving the matching degree between navigation response and user operations.

[0053] (2) Based on the first rhythm vector, the present invention uses the support vector machine algorithm to determine the high-frequency operation scenario and combines it with the navigation demand mapping table to obtain the predicted navigation demand sequence. This step utilizes the algorithm's ability to accurately classify scenarios, associates the first rhythm vector with the actual navigation demand, and enables the system to predict the user's potential needs in specific scenarios in advance, ensuring that the recommendation of navigation options is more targeted and improving the accuracy of navigation demand prediction.

[0054] (3) This invention adjusts the display order of navigation options based on the predicted navigation demand sequence, incorporates haptic feedback patterns to obtain the option layout configuration, and combines the second rhythm vector in the current scene to filter the option subset and determine the timing parameters. This method dynamically matches the navigation layout with the user's real-time rhythm, while introducing haptic feedback to enhance interactive perception, making the timing and manner of displaying navigation options more in line with the user's operating rhythm, improving the ease of operation and the smoothness of the interactive experience.

[0055] (4) This invention obtains the final navigation path sequence by updating and predicting the navigation demand sequence based on the user click time interval sequence of the final response interface and extracting the adaptive navigation path features. This closed-loop optimization mechanism can continuously learn the latest user operating habits and continuously correct the navigation strategy, so that the system can adapt to changes in different users and scenarios in long-term use and ensure continuous optimization of navigation effect. Attached Figure Description

[0056] Figure 1 This is a flowchart illustrating an embodiment of the fast navigation control method for mobile terminal software provided by the present invention.

[0057] Figure 2 This is a schematic diagram of an embodiment of the fast navigation control system for mobile terminal software provided by the present invention. Detailed Implementation

[0058] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] Reference Figure 1 The first embodiment of the present invention provides a fast navigation control method for mobile terminal software, including steps S11 to S17, as follows:

[0060] S11: Obtain the user's click events and corresponding timestamp data during the interaction process, perform preprocessing, and obtain the operation sequence dataset;

[0061] S12, Based on the operation sequence dataset, extract the high-frequency click interval and function switching pattern to determine the first rhythm vector of the user operation;

[0062] S13, Based on the first rhythm vector, the support vector machine algorithm is used to determine the high-frequency operation scenario, and the high-frequency operation scenario is matched by a preset navigation demand mapping table to obtain the predicted navigation demand sequence;

[0063] S14. Based on the predicted navigation demand sequence, the display order of navigation options is adjusted to obtain a preliminary interface layout, and the preliminary interface layout is matched with a preset haptic feedback mapping relationship to obtain an option layout configuration.

[0064] S15, obtain the user's second rhythm vector in the current scenario, match and filter the option layout configuration with the second rhythm vector to obtain an option subset, calculate the trigger time node of the option subset based on the high-frequency click interval, and determine the timing parameter of the second rhythm vector;

[0065] S16, based on the second rhythm vector and the timing parameter, obtain the user's current interface state, adjust the display priority of the option subset, generate a synchronized haptic feedback sequence, optimize the current interface state based on the display priority and the haptic feedback sequence, and obtain the final response interface;

[0066] S17. Based on the final response interface, obtain the time interval sequence of the click event, update the predicted navigation demand sequence based on the time interval sequence, and extract the navigation path features adapted to the current scene to obtain the final navigation path sequence.

[0067] In step S11, the user's click events and corresponding timestamp data during the interaction are acquired, preprocessed, and the operation sequence dataset is obtained, including:

[0068] The user's click events during the interaction process are obtained and recorded according to the corresponding timestamp data to obtain an initial dataset;

[0069] For the initial dataset, the time interval between every two adjacent click events is calculated. If the time interval is less than a preset time interval threshold, the latter of the two adjacent click events is determined to be an abnormal click, and the abnormal click is removed to obtain a filtering operation sequence.

[0070] Based on the filtering operation sequence, by analyzing the frequency and time distribution of the click events, the user operation behavior pattern is extracted to obtain a behavior feature dataset.

[0071] The clustering center points of the behavioral feature dataset are calculated iteratively using a clustering algorithm. Based on the clustering center points, the behavioral feature dataset is classified to obtain the operation sequence dataset.

[0072] It should be noted that click events refer to user actions performed on mobile software interface elements (such as buttons, icons, input boxes, etc.) by touching the screen. Timestamp data records the specific moment the operation occurred. The resulting initial dataset ensures data integrity and temporal sequence, accurately reconstructing the order of user actions. For example, in a food delivery app, a user's click events include "Open App (08:30:01) - Click on homepage recommendation (08:30:03) - View merchant details (08:30:07) - Click on dish (08:30:10) - Add to cart (08:30:12) - Submit order (08:30:20)". These events and their corresponding timestamps constitute the initial dataset.

[0073] In this embodiment, the time interval between adjacent click events refers to the time difference between two consecutive click events. The preset time interval threshold needs to be adjusted according to the specific application scenario and user group characteristics. For example, the threshold can be appropriately increased for applications used by the elderly. When the time interval is less than the preset time interval threshold, it indicates that the latter event was caused by accidental touch, device failure, or automated script operation, and is therefore judged as an abnormal click. Removing these abnormal clicks can reduce the interference of noise data on subsequent analysis. Specifically, if a user clicks "Submit Order" twice consecutively with an interval of 0.5 seconds, which is less than the threshold of 1 second, the latter click is judged as an abnormal click and removed, resulting in a filtered operation sequence. The frequency of click events refers to the number of times a user clicks per unit time, while the time distribution refers to the distribution of click events in different time periods. Combining the two can quantify the user's operating habits. For example, frequency calculation shows that the user clicks an average of 5 times per minute, and time distribution analysis shows that the user clicks most intensively between 8-10 pm, accounting for 50% of the total number of clicks throughout the day. These quantitative indicators together constitute the user's behavioral pattern.

[0074] Furthermore, user groups are further segmented using clustering algorithms. Clustering is an unsupervised learning algorithm whose core principle is to automatically group data points with similar characteristics into the same category, while data points in different categories have significant differences, without the need for pre-defined classification labels. By randomly selecting several initial cluster centers, the Euclidean distance between each data point and each cluster center is calculated, and the data point is assigned to the category of the nearest cluster center. Then, the mean of each category is recalculated as the new cluster center, and the above division and update process is repeated until the change in cluster centers is less than a preset change threshold. The preset change threshold is set based on the average absolute deviation of the features of each dimension of the cluster centers, and can be set to 1% to 5% of the average absolute deviation. If the feature vectors of the behavioral feature dataset (such as average click interval, peak click ratio, etc.) are concentrated in the range of 0.1 to 10, and the average absolute deviation of the features of each dimension of the cluster centers is about 0.2, then the preset change threshold can be set to 0.002. For scenarios with high real-time requirements, such as high-frequency operations, the preset change threshold can be increased to 5% of the average absolute deviation to balance clustering accuracy and algorithm response speed.

[0075] In this embodiment, the data samples in the behavioral feature dataset are vectors composed of features such as average click interval and peak click percentage. Using these vectors as input, through iterative calculation by a clustering algorithm, users with similar operational characteristics can be grouped into one category. For example, users with short average click intervals and high frequency of operations are grouped into one category, while users with long average click intervals and a slower operational rhythm are grouped into another category. The resulting operational sequence dataset can provide an accurate basis for group segmentation for subsequent personalized adjustments to navigation control.

[0076] In step S12, based on the operation sequence dataset, high-frequency click intervals and function switching patterns are extracted to determine the first rhythm vector of user operations, including:

[0077] The operation sequence dataset is segmented by a preset time window, and the time distribution features are extracted to obtain the initial behavior state sequence;

[0078] For the initial behavioral state sequence, a hidden Markov model is used to calculate the state transition probability between adjacent behavioral states, and the state transition process with the state transition probability higher than a preset probability threshold is determined as the function switching rule.

[0079] Calculate the time difference between adjacent clicks in the initial behavior state sequence. If the time difference meets the preset high-frequency click interval range within the preset number of consecutive click intervals, then the time difference within the preset high-frequency click interval range is classified as the high-frequency click interval.

[0080] The high-frequency click interval and the function switching pattern are fused with the time distribution characteristics to obtain the first rhythm vector.

[0081] It should be noted that the preset time window length is fixed, but can be adjusted according to the frequency of operations in the application scenario. Shorter windows can be used for scenarios with frequent operations, while longer windows can be used for scenarios with less frequent operations. For example, a 20-second window could be used for social apps, and a 60-second window for reading apps. The time distribution characteristics include the number of click events within each window, the start and end times of the operation, and the trend of click frequency changes, reflecting the distribution pattern of user operations over time. The initial behavior state sequence not only includes the operation events themselves but also incorporates time distribution information.

[0082] It's worth noting that Hidden Markov Models (HMMs) are probability-based time series models suitable for processing sequence data with hidden states. They consist of three elements: initial state probability π, state transition probability A, and observation probability B, denoted as λ=(π, A, B). This method includes three core elements: a set of hidden states, an observation sequence, and a probability matrix. The set of hidden states is defined as the user's state within the app's functional modules, such as {homepage, product list, details page, shopping cart, checkout page}, denoted as S={ , ,…, }; The observation sequence consists of user click behaviors that can be recorded, such as {clicking search, clicking on a product, swiping a page, clicking to pay}, denoted as O={ , ,…, The probability matrix includes the state transition probability matrix AM (representing the transition probability from the hidden state). Transition to state The probability of emission (BM) and the emission probability matrix BM (representing the probability in the hidden state) The following generates observation behavior The probability of the observed sequence is used as input, and the states of the functional modules labeled by the user are used as hidden state labels. Unsupervised training is carried out. The state transition probability matrix AM and the emission probability matrix BM are iteratively optimized by maximizing the likelihood probability of the observed sequence until the change in likelihood probability is less than 1e-6, at which point the model converges.

[0083] Furthermore, based on the trained Hidden Markov Model, the probability of transitioning from one hidden state to another is calculated after inputting a new user click sequence, with a value ranging from 0 to 1. When the probability of a state transition is higher than a preset probability threshold, it indicates that the transition process has high regularity and can be identified as a function switching pattern. The preset probability threshold is set based on the statistical distribution characteristics of historical behavioral data. The mean μ and standard deviation σ of all state transition probabilities are calculated. Depending on the scenario's requirements for the significance of the pattern, the threshold can be set from μ+1.2σ to μ+2σ. For scenarios with high requirements for the rigor of function switching logic, such as the transaction process of financial apps, a higher threshold of μ+2σ can be used; for scenarios with high tolerance for user behavior diversity, such as the browsing path of content apps, a lower threshold of μ+1.2σ can be used.

[0084] In this embodiment, the preset number of consecutive click intervals is generally set to 3 or more, and the preset high-frequency click interval range is set based on the physiological characteristics of rapid human operation, while also needing to be adjusted according to the application type. When multiple consecutive time differences fall within the high-frequency click interval range, it indicates that the user is in a high-frequency click state. These time differences are classified as high-frequency click intervals, and their purpose is to quantify the rhythmic characteristics of the user's rapid operation. Integrating high-frequency click intervals, function switching patterns, and time distribution characteristics requires normalization processing to convert features of different dimensions into values ​​in the 0-1 range, such as dividing the high-frequency click interval by the maximum possible interval, to make each feature comparable. These normalized features are used as independent dimensions of a vector, sorted according to the degree of correlation between the features and the user's core operations, such as the conventional correlation sorting as [high-frequency click interval, main switching frequency, window update frequency], forming a multi-dimensional first rhythm vector, with each dimension corresponding to a feature.

[0085] For example, in a reading app, the operation sequence dataset contains user C's operation records: "Open novel (21:00:00) - Click to turn page (21:00:02) - Click to turn page (21:00:04) - Click to turn page (21:00:06) - Click to annotate (21:00:12) - Click to turn page (21:00:14) - Close novel (21:00:20)". After being segmented into a preset 60-second time window, the entire sequence belongs to one window, and the time distribution feature is "7 click events, concentrated between 21:00 and 21:00:20". When using a Hidden Markov Model (HMM) for analysis, the hidden states are defined as "reading state" (corresponding to the page-turning operation) and "auxiliary operation state" (corresponding to clicking the annotation). The HMM calculates that the transition probability from "auxiliary operation state" to "reading state" is 0.8, which is higher than the preset probability threshold of 0.5. Therefore, "auxiliary operation state → reading state" is determined to be the function switching pattern. The time difference between adjacent clicks is calculated. "21:00:00-21:00:02", "21:00:02-21:00:04", and "21:00:04-21:00:06" are all 2 seconds. Three consecutive clicks (meeting a preset number) fall within the high-frequency range of 2-4 seconds. The average interval between high-frequency clicks is calculated to be 2 seconds. The final fused first rhythm vector is [average high-frequency interval 2 seconds, main switching probability 0.8, window frequency 0.35 times / second]. This vector can determine that the user is in a "high-frequency page-turning reading scenario".

[0086] In step S13, based on the first rhythm vector, a support vector machine algorithm is used to determine high-frequency operation scenarios. These scenarios are then matched using a preset navigation demand mapping table to obtain a predicted navigation demand sequence, including:

[0087] When the average value of the high-frequency click interval is less than the preset click interval threshold, the state transition probability of adjacent click events in the high-frequency click interval is extracted according to the first rhythm vector.

[0088] The classification boundary features are determined by the support vector machine algorithm. The high-frequency operation scenarios are then selected from the first rhythm vector by combining the classification boundary features and the state transition probabilities.

[0089] The high-frequency operation scenarios are matched with a preset navigation demand mapping table to obtain the user's potential needs. The potential needs are then arranged in the order of user operation time to obtain the predicted navigation demand sequence.

[0090] It's important to note that the preset click interval threshold is a critical value used to determine "high-frequency operation scenarios." Its purpose is to further differentiate whether the identified high-frequency clicks warrant a special response. When the average high-frequency click interval is less than this threshold, it indicates that the user's operation pace is fast enough that the system needs to proactively adapt (e.g., prioritize displaying core functions). The state transition probability at this point reflects the likelihood of the user switching from one function to another under a fast-paced operation. Support Vector Machines (SVMs) are a supervised learning algorithm whose core principle is to find an optimal hyperplane as the classification boundary, ensuring maximum separation between data points of different categories on either side of this hyperplane, thereby achieving the classification of unknown data.

[0091] It's worth noting that the Support Vector Machine (SVM) model consists of an input layer, a kernel function mapping layer, and an output layer. The multidimensional features of the first rhythm vector serve as the algorithm input, including the user's rapid continuous operation behavior and gradual or intermittent operation behavior. The kernel function uses radial basis functions to map the non-linearly separable feature space to a high-dimensional linearly separable space. The output is a binary classification result composed of "high-frequency operation scene vector features" and "non-high-frequency operation scene vector features," and the classification boundary features are trained. The classification boundary features are a set of vector feature combinations that can distinguish between high-frequency and non-high-frequency scenes. For example, a high-frequency operation scene has a vector feature combination of [average click interval < 3 seconds, state transition probability > 0.6].

[0092] Furthermore, the state transition probabilities and average click intervals in the first rhythm vector are compared with the classification boundary features. If the vector falls on one side of the hyperplane corresponding to the high-frequency operation scenario, it is determined to be a high-frequency operation scenario. The navigation demand mapping table is a pre-constructed table of correspondence between scenarios and demands, established based on statistical analysis of historical user behavior data. It contains the potential demand sequences of users under different high-frequency operation scenarios. For example, "high-frequency page-turning scenario" corresponds to the potential demand sequence of "quickly jump to chapters and adjust font size," and "high-frequency product browsing scenario" corresponds to the potential demand sequence of "add to cart and view reviews."

[0093] For example, in a social app, step S12 presets a high-frequency click interval range of 2-4 seconds. User D clicks "Browse Feed - Like - Comment" consecutively, with time differences of 2 seconds and 3 seconds respectively, both falling within this range, and is therefore identified as a high-frequency click. The average high-frequency click interval is 2.5 seconds. In step S13, the preset click interval threshold is set to 3 seconds. Since 2.5 seconds < 3 seconds, it indicates that the user's operation rhythm has reached the high-frequency scenario level. At this time, the state transition probability from "Browse Feed" to "Interactive Operation" is extracted as 0.7. The classification boundary feature of the support vector machine model, "average high-frequency click interval < 3 seconds and state transition probability > 0.5", determines it as a "high-frequency social interaction scenario". Finally, it matches the navigation requirement mapping table to obtain the sequence [like, comment, view author's homepage], achieving targeted optimization of the interface.

[0094] In step S14, based on the predicted navigation demand sequence, the display order of navigation options is adjusted to obtain a preliminary interface layout. Then, based on a preset haptic feedback mapping relationship and the preliminary interface layout, an option layout configuration is obtained, including:

[0095] Based on the predicted navigation demand sequence, the frequency of occurrence and operation completion time of each navigation demand are extracted, and the priority weight of each navigation option is calculated based on the frequency of occurrence and the operation completion time.

[0096] According to the priority weights from high to low, the display order of the corresponding navigation options is arranged in descending order, and the interface is rendered to obtain the preliminary interface layout.

[0097] Obtain the functional attributes of each layout element in the initial interface layout, and match the corresponding haptic feedback parameters for each navigation option based on the priority weight and the functional attributes and the preset haptic feedback mapping relationship.

[0098] The initial interface layout is associated and integrated with the haptic feedback parameters to generate an option layout configuration that includes display sorting strategy and haptic feedback strategy.

[0099] It's important to note that the frequency of navigation requests refers to the proportion of times a particular navigation request appears in the sequence out of the total number of occurrences, reflecting the prevalence of that request. Operation completion time refers to the average time from triggering the request to completing the operation; shorter times indicate simpler operations, while longer times require priority display to reduce user burden. The priority weight ω can be calculated using the weighted summation formula: ω = 0.6 × f + 0.4 × (t / t0), where f represents the frequency of navigation requests, t represents the operation completion time, and t0 represents the standard operation completion time, which is a baseline completion time preset based on the functional complexity of navigation options, the number of operation steps, and industry-standard interaction methods, used to measure the relative speed of actual user operation completion. Navigation options corresponding to their priority weights are arranged in descending order, with the highest-weighted option placed in the most prominent position on the interface (such as the top or upper-middle area), and lower-weighted options arranged in secondary positions (such as the lower part or in a collapsed menu). Interface rendering uses front-end frameworks such as React and Vue to transform the sorting results into user-visible interface elements, including adjusting the position, size, and color of the options.

[0100] In this embodiment, the functional attributes of layout elements guide the operation type (such as click to confirm, swipe to switch, long press to edit, etc.) and importance (such as payment, deletion, and other critical operations) of navigation options. The preset haptic feedback mapping relationship is a set of rules that associates functional attributes with vibration parameters such as vibration intensity, frequency, and duration. Vibration intensity is expressed as a percentage of the device's maximum vibration intensity, and the frequency range conforms to the comfortable range of human tactile perception, generally 20-500Hz. For example, clicking a critical operation button corresponds to a vibration intensity of 50%-60%, a frequency of 200Hz, and a duration of 0.3 seconds, while a secondary operation corresponds to a vibration intensity of 30%, a frequency of 100Hz, and a duration of 0.1 seconds. Enhancing operation feedback through haptic signals helps users improve operational accuracy in scenarios involving movement, poor visibility, or distracted visual attention. Finally, a mapping relationship is established between the visual position and display style of navigation options and the corresponding haptic feedback parameters, forming the option layout configuration.

[0101] For example, in an e-commerce app, the predicted navigation request sequence is [Add to cart, View reviews, Pay, Share]. Based on the average time for a single user click to complete an operation in historical data and the industry standard for simple clicks, the standard completion times for each function are set as follows: Add to cart 2 seconds, View reviews 5 seconds, Pay 6 seconds, Share 3 seconds. The frequencies of occurrence for each navigation request are extracted as follows: Add to cart 30%, View reviews 25%, Pay 35%, Share 10%; the operation completion times are as follows: Add to cart 2 seconds, View reviews 3 seconds, Pay 7 seconds, Share 2 seconds. The priority weights of each navigation option are calculated as follows: Add to Cart ω1 = 0.6 × 0.3 + 0.4 × (2 / 2) = 0.18 + 0.4 = 0.58, View Reviews ω2 = 0.6 × 0.25 + 0.4 × (3 / 5) = 0.15 + 0.24 = 0.39, Pay ω3 = 0.6 × 0.35 + 0.4 × (7 / 6) ≈ 0.21 + 0.467 = 0.677, Share ω4 = 0.6 × 0.1 + 0.4 × (2 / 3) = 0.06 + 0.267 = 0.327. Arranging these in descending order of weight yields the following preliminary interface layout: Pay (top center), Add to Cart (top right), View Reviews, and Share (bottom). Based on the functional attributes, "Payment" and "Add to Cart" are key operations, matched with a vibration intensity of 50% and a duration of 0.3 seconds; "View Reviews" and "Share" are secondary operations, matched with a vibration intensity of 30% and a duration of 0.1 seconds.

[0102] In step S15, the user's second rhythm vector in the current scenario is obtained. The option layout configuration is matched and filtered with the second rhythm vector to obtain an option subset. The trigger time node of the option subset is calculated based on the high-frequency click interval to determine the timing parameters of the second rhythm vector, including:

[0103] Obtain the real-time click events and timestamps of the user's current operation, and generate the second rhythm vector;

[0104] Calculate the distance between the second rhythm vector and the classification boundary feature, normalize the distance, and obtain the matching degree between the second rhythm vector and the option layout configuration;

[0105] When the matching degree is higher than the preset matching degree threshold, the option layout configuration is filtered by the preset function switching simplification rules to obtain the option subset;

[0106] Based on the high-frequency click interval in the second rhythm vector, and combined with the haptic feedback parameters, the trigger time nodes of each navigation option in the option subset are calculated, and the duration between the initial trigger node and the last trigger node is determined as the timing parameter.

[0107] It should be noted that real-time click events refer to the latest click behavior generated by the user during the current interaction. The second rhythm vector is a multi-dimensional vector generated based on these real-time click behavior data. Its dimensions include the current high-frequency click interval, function switching frequency, and the number of clicks per unit time, all obtained through statistical calculations of real-time data. The classification boundary feature is the vector threshold range obtained in the previous steps to define different scene types. When calculating the Euclidean distance between the second rhythm vector and the classification boundary feature, since the units of each dimension in the second rhythm vector are different, standardization processing is required to convert each dimension value into a dimensionless relative value. Specifically, the parameter value of each dimension is first subtracted from the historical mean of that dimension, and then divided by the historical standard deviation of that dimension to obtain the standardized dimension value. The distance d is normalized using the formula α=d / (1+d), and the resulting matching degree α ranges from 0 to 1. The larger the distance between the second rhythm vector and the classification boundary feature, the closer the matching degree is to 1.

[0108] Furthermore, when the matching degree is higher than the preset matching degree threshold, it indicates that the current scenario and the option layout configuration are well adapted. The preset function switching simplification rules can then be used to further filter the option layout configuration. The preset matching degree threshold is the critical value for judging adaptability. It is calculated by taking the lowest matching degree M_min corresponding to scenarios where user operation efficiency improved by ≥30% after adaptation from historical data. The matching degree threshold is preset to 0.9×M_min, and the final matching degree threshold is generally 0.6-0.7. Those skilled in the art will understand that this threshold can be flexibly adjusted according to the application scenario. For example, in scenarios with high operational precision requirements, such as the transfer process in financial apps, the matching degree threshold can be appropriately increased; while in scenarios with high real-time requirements, such as the rapid switching in short video apps, the matching degree threshold can be appropriately decreased.

[0109] Furthermore, the simplified function switching rules are a set of rules for streamlining navigation options based on scene characteristics. The filtering process first extracts the functional attributes of all navigation options in the option layout configuration; then, combined with the current scene characteristics reflected by the second rhythm vector (such as the "quick browse" feature in high-frequency operation scenarios), it calculates the click frequency of each navigation option in the same historical scene and divides it by the average click frequency across all scenes to obtain the correlation between the navigation option and the operation scene; finally, it retains navigation options with a correlation higher than a preset correlation threshold, resulting in an option subset. The preset correlation threshold can be set to 1.2. By statistically analyzing historical data, it obtains the user's actual click option preferences in different scenarios. Setting the correlation threshold to 1.2 focuses on the core user needs in the current scene while avoiding operational interference caused by option redundancy. If the scene requires extreme simplification, such as the one-handed operation scenario on small-screen devices, the correlation threshold can be increased to 1.35 to further reduce unnecessary options.

[0110] In this embodiment, the trigger time node refers to the specific moment when each navigation option becomes clickable on the interface. Its calculation requires combining the high-frequency click interval and the vibration duration in the haptic feedback parameters. For example, if the high-frequency click interval is 2 seconds and the haptic feedback duration of a certain option is 0.3 seconds, then the trigger time node for the next option must be 1.7 seconds after the previous feedback ends. The initial trigger node is the trigger time of the first option in the option subset, and the final trigger node is the trigger time of the last option. The duration between these two is the timing parameter, defining the effective display window of the entire option subset on the interface.

[0111] For example, in a travel booking app, the real-time click events and timestamps of the user's current operation are: "Search destination (10:00:00) - View hotel list (10:00:02) - Click hotel details (10:00:05)". The generated second rhythm vector has the following original values: [2.5 seconds (average high-frequency click interval), 0.33 times / second (function switching frequency), 0.6 times / second (number of clicks per unit time)]. The historical mean μ for each dimension is [3 seconds, 0.2 times / second, 0.4 times / second], and the historical standard deviation σ is [1 second, 0.1 times / second, 0.2 times / second]. The standardized vector is [-0.5, 1.3, 1]. The standardized parameters for the classification boundary conditions are [0, 0, 0]. The Euclidean distance is calculated. The matching degree can be obtained. The match rate is higher than the preset matching threshold of 0.6. Based on the simplified function switching rules, a subset of core options is selected from the option layout configuration: [View Hotel Details, Book Room, Pay]. Combining the high-frequency click interval of 2.5 seconds and the haptic feedback parameter (vibration duration of 0.2 seconds for each option), the initial trigger node is calculated to be 10:00:05, and the final trigger node is 10:00:10. Therefore, the timing parameter is 5 seconds.

[0112] In step S16, based on the second rhythm vector and the timing parameter, the user's current interface state is obtained, the display priority of the option subset is adjusted, and a synchronized haptic feedback sequence is generated. The current interface state is then optimized based on the display priority and the haptic feedback sequence to obtain the final response interface, including:

[0113] If the timing parameter is greater than a preset time threshold, then when the next click event of the user operation is triggered, the user's current interface state is obtained;

[0114] Based on the current interface state and in conjunction with the second rhythm vector, the display priority of the option subset is adjusted to obtain the adjusted option subset;

[0115] Based on the adjusted option subset, the current interface state is rendered to obtain a response interface. Through a preset haptic feedback mapping relationship, a haptic feedback sequence synchronized with the response interface is generated.

[0116] The adjusted option subset and the haptic feedback sequence are injected into the response interface to obtain the final response interface.

[0117] It should be noted that the timing parameter value directly reflects the stability of the current high-frequency operation scenario. The larger the value, the more stable and consistent the user's behavior is under this high-frequency operation mode, providing a basis for interface adjustments. By statistically analyzing historical data of scenarios where users maintained high-frequency operations without interruption or abnormal function transitions, the average timing parameter value of these samples was calculated. To ensure that the time threshold covers most stable scenarios while avoiding interface response delays due to excessive waiting, 80% of this average value was taken as the preset time threshold, which can be set to 5 seconds. This is used to determine whether the stability of high-frequency operations is sufficient to support interface response.

[0118] Furthermore, using the next click event as the trigger point allows the interface response to precisely match the user's operation rhythm, avoiding interaction interference caused by adjustments during unstable scenarios. The current interface state refers to the layout, displayed content, and interaction state of interface elements when the user triggers the click event, such as the current page, visible buttons, and input box states. Based on the current interface state and the second rhythm vector, the priority of core function options in high-frequency operation scenarios should be increased, while avoiding conflicts with existing high-priority elements. For example, if the current interface is a "product details page," and the second rhythm vector indicates the user is in a high-frequency operation state, then the "Add to Cart" option should be given the highest priority and placed in a prominent position in the middle of the page, while the "Share" option should be de-prioritized and placed in a secondary menu.

[0119] In this embodiment, the adjusted option subset retains the core functionality while optimizing the display priority based on real-time status, ensuring that users can most easily find and operate the desired options on the current interface. The adjusted option subset is integrated into the current interface using front-end technologies such as React and Flutter, including updating the position, size, and style of the options. The generated response interface is an intermediate transitional interface where the visual adjustments have been completed but the haptic feedback strategy has not yet been integrated. The preset haptic feedback mapping relationship is a set of rules corresponding to navigation options and vibration parameters. Based on these rules, a corresponding haptic feedback sequence is generated for each option in the response interface, ensuring that haptic feedback is synchronized with the visual display and enhancing the user's perception of the options through physical vibration. The final injection process integrates the display logic of the adjusted option subset and the triggering logic of the haptic feedback sequence into the code layer of the response interface, enabling the final response interface to both display the adjusted navigation options and automatically trigger the corresponding haptic feedback when the user interacts with them.

[0120] For example, in a food delivery app, the timing parameter is 6 seconds, which is greater than the preset time threshold of 5 seconds, indicating that the user's current high-frequency ordering operation scenario has stabilized. The user's next click event is "View food details," triggering the acquisition of the current interface state as "Merchant page, displaying the food list and the 'Enter Store' button," with the second rhythm vector being [1.5 seconds (average click interval), 0.6 times / second (function switching frequency)]. Based on this information, the display priority of the option subset is adjusted. The atomic set is ["View details," "Add to cart," "Favorite merchant"]. After adjustment, "Add to cart" is given the highest priority and placed below the food name, followed by "View details," and "Favorite merchant" is placed in the upper right corner menu. Based on this, the rendering response interface is enlarged and displayed in orange, and through a preset haptic feedback mapping relationship, a feedback with a vibration intensity of 50% and a vibration duration of 0.2 seconds is matched to "Add to cart," generating a synchronized haptic feedback sequence. By injecting a subset of options and a feedback sequence into the response interface, when a user clicks "Add to Cart," the button can be quickly located visually, and the user can also feel a clear vibration feedback, improving operational efficiency and a sense of confirmation.

[0121] In step S17, based on the final response interface, the time interval sequence of the click event is obtained, the predicted navigation demand sequence is updated based on the time interval sequence, and navigation path features adapted to the current scene are extracted to obtain the final navigation path sequence.

[0122] It should be noted that the time interval sequence refers to the sequence of time differences between consecutive user clicks in the final response interface, used to quantify the rhythm changes of the user in actual operation. For example, the interval between a user clicking "Add to Cart" and "Pay" is 3 seconds, and the interval between "Pay" and "Confirm Order" is 5 seconds, forming a sequence [3,5]. The predicted navigation demand sequence is the potential user demand path generated based on the scenario analysis in the early stage, while the time interval sequence reflects the order and rhythm of the user's actual operation demand.

[0123] Furthermore, the deviation between the actual time interval sequence and the corresponding step time interval in the predicted sequence is calculated. When the average deviation is greater than the preset deviation threshold of 1.8 seconds, it indicates a large deviation between the prediction and the actual result. The steps in the required sequence need to be adjusted according to the actual click order, such as deleting steps not performed by the user or adding steps actually triggered by the user, and correcting the predicted intervals for each step. The deviation threshold of 1.8 seconds is obtained by statistically analyzing the 80%-90% quantile of the deviation between the actual and predicted intervals in historical scenarios with continuous and stable user operation rhythms, balancing response timeliness and accuracy. Those skilled in the art will understand that this deviation threshold can be adjusted within the range of 1.2 to 2.5 seconds depending on the specific application scenario, such as fast-paced, low-tolerance scenarios like skill triggering in game apps, or slow-paced, precise matching scenarios like chapter jumping in reading apps.

[0124] In this embodiment, navigation path features refer to the sequence of steps a user takes to complete a target operation, key nodes (such as necessary functional modules), and path length (number of steps). The final navigation path sequence is a streamlined and efficient operation path generated based on these features, reducing redundant steps and improving navigation efficiency. For example, in an e-commerce scenario, by combining the rhythm vector of the current high-frequency operation scenario, the step sequence is extracted as "search for product → view details → add to cart → pay," with "pay" as the key node, a path length of 4 steps, and no abnormal intervals. The resulting navigation path sequence [search for product → view details → add to cart → pay] conforms to the rhythm of high-frequency scenarios, improving the smoothness of the payment process.

[0125] In summary, this invention discloses a fast navigation control method for mobile software, comprising: acquiring user click events and corresponding timestamp data during interaction, preprocessing them to obtain an operation sequence dataset; extracting high-frequency click intervals and function switching patterns from the operation sequence dataset to determine a first rhythm vector of user operations; using a support vector machine algorithm to determine high-frequency operation scenarios based on the first rhythm vector, matching the high-frequency operation scenarios with a preset navigation demand mapping table to obtain a predicted navigation demand sequence; adjusting the display order of navigation options based on the predicted navigation demand sequence to obtain a preliminary interface layout, and matching the preliminary interface layout with a preset haptic feedback mapping relationship to obtain an option layout configuration; and acquiring the user's current operation sequence in the current scenario. The second rhythm vector is used to match and filter the option layout configuration to obtain an option subset. The trigger time nodes of the option subset are calculated based on the high-frequency click interval to determine the timing parameters of the second rhythm vector. Based on the second rhythm vector and the timing parameters, the user's current interface state is obtained, the display priority of the option subset is adjusted, and a synchronized haptic feedback sequence is generated. The current interface state is optimized based on the display priority and the haptic feedback sequence to obtain the final response interface. Based on the final response interface, the time interval sequence of the click events is obtained, and the predicted navigation demand sequence is updated based on the time interval sequence. Navigation path features adapted to the current scene are extracted to obtain the final navigation path sequence. This invention achieves real-time adaptation of the navigation interface to user operating habits by dynamically capturing the user's operation rhythm and combining it with haptic feedback to optimize the navigation layout, thereby improving the interaction efficiency and navigation response accuracy of mobile software.

[0126] Reference Figure 2 The second embodiment of the present invention provides a fast navigation control system for mobile terminal software, comprising:

[0127] The data preprocessing module is used to acquire user click events and corresponding timestamp data during the interaction process, perform preprocessing, and obtain an operation sequence dataset;

[0128] The rhythm vector generation module is used to extract high-frequency click intervals and function switching patterns based on the operation sequence dataset to determine the first rhythm vector of the user operation;

[0129] The navigation demand prediction module is used to determine high-frequency operation scenarios based on the first rhythm vector using a support vector machine algorithm, and to obtain a predicted navigation demand sequence by matching the high-frequency operation scenarios with a preset navigation demand mapping table.

[0130] The layout configuration generation module is used to adjust the display order of navigation options according to the predicted navigation demand sequence to obtain a preliminary interface layout, and to match the preliminary interface layout with a preset haptic feedback mapping relationship to obtain the option layout configuration.

[0131] The timing parameter determination module is used to obtain the user's second rhythm vector in the current scenario, match and filter the option layout configuration with the second rhythm vector to obtain an option subset, calculate the trigger time node of the option subset based on the high-frequency click interval, and determine the timing parameter of the second rhythm vector.

[0132] The response interface optimization module is used to obtain the user's current interface state based on the second rhythm vector and the timing parameter, adjust the display priority of the option subset, generate a synchronized haptic feedback sequence, optimize the current interface state based on the display priority and the haptic feedback sequence, and obtain the final response interface.

[0133] The navigation path update module is used to obtain the time interval sequence of the click event based on the final response interface, update the predicted navigation demand sequence based on the time interval sequence, and extract navigation path features adapted to the current scene to obtain the final navigation path sequence.

[0134] It should be noted that the mobile terminal software fast navigation control system provided in this embodiment of the invention is used to execute all the process steps of the mobile terminal software fast navigation control method in the above embodiment. The working principle and beneficial effects of the two are one-to-one, so they will not be described again.

[0135] This invention also provides an electronic device. The electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a navigation layout program. When the processor executes the computer program, it implements the steps in the aforementioned embodiments of the fast navigation control method for mobile terminal software, for example... Figure 1 The step S11 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above-described device embodiments, such as the data preprocessing module.

[0136] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0137] The electronic device may be a desktop computer, laptop, handheld computer, or smart tablet, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. It may include more or fewer components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0138] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting all parts of the electronic device via various interfaces and lines.

[0139] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0140] Wherein, if the modules / units integrated in the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0141] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0142] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A fast navigation control method for mobile terminal software, characterized in that, include: The user's click events and corresponding timestamp data during the interaction process are obtained, preprocessed, and the operation sequence dataset is obtained. Based on the operation sequence dataset, high-frequency click intervals and function switching patterns are extracted to determine the first rhythm vector of user operations; wherein, the first rhythm vector is a multi-dimensional feature vector containing high-frequency click intervals, main switching frequencies, and window update frequencies. Based on the first rhythm vector, a support vector machine algorithm is used to determine high-frequency operation scenarios. The high-frequency operation scenarios are matched with a preset navigation demand mapping table to obtain a predicted navigation demand sequence. Based on the predicted navigation demand sequence, the display order of navigation options is adjusted to obtain a preliminary interface layout, and the option layout configuration is obtained by matching the preliminary interface layout with the preset haptic feedback mapping relationship. The second rhythm vector of the user in the current scenario is obtained, and the option layout configuration is matched and filtered with the second rhythm vector to obtain an option subset. The trigger time node of the option subset is calculated based on the high-frequency click interval to determine the timing parameter of the second rhythm vector. The second rhythm vector is generated based on real-time click data and includes a multi-dimensional feature vector containing high-frequency click interval, function switching frequency, and number of clicks per unit time. Based on the second rhythm vector and the timing parameter, the user's current interface state is obtained, the display priority of the option subset is adjusted, and a synchronized haptic feedback sequence is generated. The current interface state is optimized based on the display priority and the haptic feedback sequence to obtain the final response interface. Based on the final response interface, the time interval sequence of the click event is obtained, the predicted navigation demand sequence is updated based on the time interval sequence, and navigation path features adapted to the current scene are extracted to obtain the final navigation path sequence.

2. The fast navigation control method for mobile terminal software according to claim 1, characterized in that, The process of acquiring user click events and corresponding timestamp data during interaction, preprocessing them to obtain an operation sequence dataset, includes: The user's click events during the interaction process are obtained and recorded according to the corresponding timestamp data to obtain an initial dataset; For the initial dataset, the time interval between every two adjacent click events is calculated. If the time interval is less than a preset time interval threshold, the latter of the two adjacent click events is determined to be an abnormal click, and the abnormal click is removed to obtain a filtering operation sequence. Based on the filtering operation sequence, by analyzing the frequency and time distribution of the click events, the user operation behavior pattern is extracted to obtain a behavior feature dataset. The clustering center points of the behavioral feature dataset are calculated iteratively using a clustering algorithm. Based on the clustering center points, the behavioral feature dataset is classified to obtain the operation sequence dataset.

3. The fast navigation control method for mobile terminal software according to claim 1, characterized in that, The step of extracting high-frequency click intervals and function switching patterns from the operation sequence dataset to determine the first rhythm vector of user operations includes: The operation sequence dataset is segmented by a preset time window, and the time distribution features are extracted to obtain the initial behavior state sequence; For the initial behavioral state sequence, a hidden Markov model is used to calculate the state transition probability between adjacent behavioral states, and the state transition process with the state transition probability higher than a preset probability threshold is determined as the function switching rule. Calculate the time difference between adjacent clicks in the initial behavior state sequence. If the time difference meets the preset high-frequency click interval range within the preset number of consecutive click intervals, then the time difference within the preset high-frequency click interval range is classified as the high-frequency click interval. The high-frequency click interval and the function switching pattern are fused with the time distribution characteristics to obtain the first rhythm vector.

4. The fast navigation control method for mobile terminal software according to claim 3, characterized in that, The step of determining high-frequency operation scenarios based on the first rhythm vector using a support vector machine algorithm, and matching the high-frequency operation scenarios with a preset navigation demand mapping table to obtain a predicted navigation demand sequence includes: When the average value of the high-frequency click interval is less than the preset click interval threshold, the state transition probability of adjacent click events in the high-frequency click interval is extracted according to the first rhythm vector. The classification boundary features are determined by the support vector machine algorithm. The high-frequency operation scenarios are then selected from the first rhythm vector by combining the classification boundary features and the state transition probabilities. The high-frequency operation scenarios are matched with a preset navigation demand mapping table to obtain the user's potential needs. The potential needs are then arranged in the order of user operation time to obtain the predicted navigation demand sequence.

5. The fast navigation control method for mobile terminal software according to claim 4, characterized in that, The step of adjusting the display order of navigation options according to the predicted navigation demand sequence to obtain a preliminary interface layout, and matching the preliminary interface layout with a preset haptic feedback mapping relationship to obtain an option layout configuration, includes: Based on the predicted navigation demand sequence, the frequency of occurrence and operation completion time of each navigation demand are extracted, and the priority weight of each navigation option is calculated based on the frequency of occurrence and the operation completion time. According to the priority weights from high to low, the display order of the corresponding navigation options is arranged in descending order, and the interface is rendered to obtain the preliminary interface layout. Obtain the functional attributes of each layout element in the initial interface layout, and match the corresponding haptic feedback parameters for each navigation option based on the priority weight and the functional attributes and the preset haptic feedback mapping relationship. The initial interface layout is associated and integrated with the haptic feedback parameters to generate an option layout configuration that includes display sorting strategy and haptic feedback strategy.

6. The fast navigation control method for mobile terminal software according to claim 5, characterized in that, The process of obtaining the user's second rhythm vector in the current scenario, matching and filtering the option layout configuration with the second rhythm vector to obtain an option subset, calculating the trigger time node of the option subset based on the high-frequency click interval, and determining the timing parameters of the second rhythm vector includes: Obtain the real-time click events and timestamps of the user's current operation, and generate the second rhythm vector; Calculate the distance between the second rhythm vector and the classification boundary feature, normalize the distance, and obtain the matching degree between the second rhythm vector and the option layout configuration; When the matching degree is higher than the preset matching degree threshold, the option layout configuration is filtered by the preset function switching simplification rules to obtain the option subset; Based on the high-frequency click interval in the second rhythm vector, and combined with the haptic feedback parameters, the trigger time nodes of each navigation option in the option subset are calculated, and the duration between the initial trigger node and the last trigger node is determined as the timing parameter.

7. The fast navigation control method for mobile terminal software according to claim 5, characterized in that, The process of obtaining the user's current interface state based on the second rhythm vector and the timing parameter, adjusting the display priority of the option subset, generating a synchronized haptic feedback sequence, optimizing the current interface state based on the display priority and the haptic feedback sequence, and obtaining the final response interface includes: If the timing parameter is greater than a preset time threshold, then when the next click event of the user operation is triggered, the user's current interface state is obtained; Based on the current interface state and in conjunction with the second rhythm vector, the display priority of the option subset is adjusted to obtain the adjusted option subset; Based on the adjusted option subset, the current interface state is rendered to obtain a response interface. Through a preset haptic feedback mapping relationship, a haptic feedback sequence synchronized with the response interface is generated. The adjusted subset of options and the haptic feedback sequence are injected into the response interface to obtain the final response interface.

8. A rapid navigation control system for mobile terminal software, characterized in that, include: The data preprocessing module is used to acquire user click events and corresponding timestamp data during the interaction process, perform preprocessing, and obtain an operation sequence dataset; The rhythm vector generation module is used to extract high-frequency click intervals and function switching patterns based on the operation sequence dataset to determine the first rhythm vector of the user operation; The navigation demand prediction module is used to determine high-frequency operation scenarios based on the first rhythm vector using a support vector machine algorithm, and to obtain a predicted navigation demand sequence by matching the high-frequency operation scenarios with a preset navigation demand mapping table. The layout configuration generation module is used to adjust the display order of navigation options according to the predicted navigation demand sequence to obtain a preliminary interface layout, and to match the preliminary interface layout with a preset haptic feedback mapping relationship to obtain the option layout configuration. The timing parameter determination module is used to obtain the user's second rhythm vector in the current scenario, match and filter the option layout configuration with the second rhythm vector to obtain an option subset, calculate the trigger time node of the option subset based on the high-frequency click interval, and determine the timing parameter of the second rhythm vector. The response interface optimization module is used to obtain the user's current interface state based on the second rhythm vector and the timing parameter, adjust the display priority of the option subset, generate a synchronized haptic feedback sequence, optimize the current interface state based on the display priority and the haptic feedback sequence, and obtain the final response interface. The navigation path update module is used to obtain the time interval sequence of the click event based on the final response interface, update the predicted navigation demand sequence based on the time interval sequence, and extract navigation path features adapted to the current scene to obtain the final navigation path sequence.

Images