Method, device and equipment for load adjustment of car key, and storage medium

Abstract

The application relates to the field of automobile intelligence, and provides a load adjustment method, device and equipment of an automobile key and a storage medium. The method comprises the following steps: collecting operation data of a user on an automobile instrument panel key in real time; constructing an operation behavior feature set of the user based on the operation data, and performing individualized operation analysis according to the operation behavior feature set to determine an individualized operation mode of the user; dynamically calculating an aging degree value and a residual life prediction value of each key according to the individualized operation mode, and determining a load distribution state of each key according to the aging degree value and the residual life prediction value of each key; and dynamically adjusting the load of each key based on real-time monitoring of the load distribution state. The method provided by the application can effectively prolong the service life of the automobile key.

Description

Technical Field

[0001] This application relates to the field of automotive intelligence, and in some specific embodiments, it relates to a method, apparatus, device, and storage medium for adjusting the load of automotive buttons. Background Technology

[0002] As automobiles become increasingly intelligent, car buttons, as a crucial interface for human-computer interaction, play a vital role in smart cars and daily driving. Their reliability and durability directly impact user experience and driving safety.

[0003] However, current methods for managing the lifespan of automotive buttons are mostly limited to simple usage counts or periodic replacements. These methods lack in-depth analysis of actual user habits and fail to dynamically adjust button functions. This static management approach struggles to adapt to the differences in usage among various users, leading to premature failure of some buttons while other button resources are underutilized, thus limiting the overall module lifespan.

[0004] Therefore, this application provides a method, apparatus, device, and storage medium for adjusting the load of automotive buttons to solve one of the aforementioned technical problems. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus, device, and storage medium for adjusting the load of automotive buttons, which can solve at least one of the aforementioned technical problems. The specific solution is as follows:

[0006] According to a specific embodiment of this application, in a first aspect, this application provides a method for adjusting the load of automotive buttons, comprising:

[0007] The system collects user operation data on the car dashboard buttons in real time; constructs a user operation behavior feature set based on the operation data, and performs personalized operation analysis based on the operation behavior feature set to determine the user's personalized operation mode; dynamically calculates the aging degree value and remaining life prediction value of each button based on the personalized operation mode, and determines the load distribution of each button according to the aging degree value and remaining life prediction value of each button; and dynamically adjusts the load of each button based on real-time monitoring of the load distribution.

[0008] In one embodiment, the real-time acquisition of user operation data on car dashboard buttons and the construction of the user's operation behavior feature set based on the operation data include: acquiring multi-dimensional data including button pressure distribution range, operation periodicity data, and duration fluctuation data in real time and constructing an original operation behavior dataset; denoising the original operation behavior dataset to obtain a denoised operation behavior feature set; extracting feature values ​​of button pressure distribution range and operation periodicity data from the denoised operation behavior feature set, and performing distribution analysis on the feature values ​​to obtain the mean and standard deviation of the feature values; and filtering out feature values ​​in the denoised operation behavior feature set that deviate from the mean by more than a preset multiple of the standard deviation to obtain the user's operation behavior feature set.

[0009] In one embodiment, the step of denoising the original operational behavior dataset to obtain a denoised operational behavior feature set includes: filtering out data points in the original operational behavior dataset whose pressure values ​​exceed a preset pressure threshold and / or whose frequency values ​​exceed a preset frequency threshold, to obtain a filtered operational behavior dataset; processing the duration fluctuation data using a time series smoothing tool on the filtered operational behavior dataset, and performing smoothing calculations on the duration fluctuation data using a sliding window method to obtain the smoothed fluctuation sequence; and filtering out data points with abnormal fluctuations in the filtered operational behavior dataset based on the deviation between the original sequence represented by the duration fluctuation data and the smoothed fluctuation sequence, to obtain the denoised operational behavior feature set.

[0010] In one embodiment, determining the user's personalized operation mode includes: based on the user's operation behavior feature set, using a clustering algorithm to classify the user's finger contact area and key combination preferences under different operation scenarios, and extracting personalized features with reference to the classification results; and determining the user's personalized operation mode by referring to the mapping relationship between personalized features and personalized operation modes.

[0011] In one embodiment, the step of dynamically calculating the aging degree value and remaining life prediction value of each button according to the personalized operation mode includes: according to the personalized operation mode, dividing the pressure range and frequency fluctuation range into layers based on the button pressure distribution and operation cycle, obtaining the pressure accumulation data of each button in each operation cycle as a layered pressure distribution combination; dividing the pressure distribution combination into time sequences according to the duration fluctuation data and operation mode differences to obtain the wear state dynamic data in each time period as a wear feature group; if the button operation frequency represented by the wear feature group in the target time period exceeds a preset frequency fluctuation range threshold, then correcting the wear state dynamic data in the target time period, extracting button position distribution data from the corrected data, and extracting a feature subset that conforms to the wear state from the button position distribution data; using a regression analysis tool to predict and calculate the feature subset to obtain the aging degree value of each button under the pressure accumulation data; and determining the remaining life prediction value of each button based on the button design life and the aging degree value.

[0012] In one embodiment, determining the load distribution of each button according to its aging degree value and remaining life prediction value includes: calculating the lifespan ratio of each button according to its aging degree value and remaining life prediction value, and extracting the distribution of each button from the lifespan ratio; and using a comparative analysis tool to determine the load distribution of each button by combining the material durability data of each button with the distribution.

[0013] In one embodiment, the step of dynamically adjusting the load of each button based on real-time monitoring of the load distribution includes: obtaining the position information of each button according to the load distribution, and monitoring the lifespan ratio of each button; wherein the lifespan ratio is determined based on the aging degree value and the remaining lifespan prediction value; if a first button with a lifespan ratio lower than a preset lifespan ratio threshold is detected, and the first button meets a preset load allocation rule, then the function allocation optimization logic is invoked, a second button is selected among the buttons, and the functions of the first button and the second button are swapped; wherein the preset load allocation rule includes that the first button and a specified number of adjacent buttons respectively meet the lifespan ratio deviation being greater than a preset deviation threshold.

[0014] According to a specific embodiment of this application, in a second aspect, this application provides a load adjustment device for automotive buttons, comprising:

[0015] A data acquisition unit is used to collect user operation data on the car dashboard buttons in real time, and construct a user operation behavior feature set based on the operation data; a determination unit is used to perform personalized operation analysis based on the operation behavior feature set to determine the user's personalized operation mode; dynamically calculate the aging degree value and remaining life prediction value of each button based on the personalized operation mode; and determine the load distribution of each button according to the aging degree value and remaining life prediction value of each button, and dynamically adjust the load of each button based on real-time monitoring of the load distribution.

[0016] According to a specific embodiment of this application, in a third aspect, this application provides an electronic device including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the method described in any one of the first aspects.

[0017] According to a specific embodiment of this application, in a fourth aspect, this application provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implements the method described in any one of the first aspects.

[0018] Compared with the prior art, the above-described solutions of this application have at least the following beneficial effects:

[0019] (1) This invention provides a method for adjusting the load of automotive buttons. By collecting user operation data on automotive dashboard buttons in real time and constructing a user operation behavior feature set based on this data, this method can deeply analyze the user's personalized operation mode. This process not only helps to accurately capture the user's actual usage habits, but also provides a solid data foundation for subsequent button wear assessment. On this basis, the aging degree value and remaining life prediction value of each button are dynamically calculated based on the personalized operation mode, so that the system can accurately assess the specific wear of each button, thereby achieving effective monitoring of the button load distribution.

[0020] (2) This invention uses clustering algorithms to directly extract personalized features from the user’s behavioral feature set, and determines the user’s personalized operation mode based on the mapping relationship between these features and personalized operation mode. This not only simplifies the data analysis process, but also improves the accuracy and practicality of the final personalized operation mode, providing a solid foundation for subsequent function allocation optimization.

[0021] (3) Based on a comprehensive consideration of the aging degree value and the remaining life prediction value, the present invention determines the load of the button under the current layout, thereby making dynamic analysis and real-time adjustment, which can adapt to the usage differences of different users, effectively extend the service life of the overall button module, reduce the risk of early failure due to overuse, improve the user experience and reduce maintenance costs. Attached Figure Description

[0022] Figure 1 A flowchart of a method for adjusting the load of automotive buttons is shown;

[0023] Figure 2 A flowchart illustrating a method for collecting operational data and constructing an operational behavior feature set is shown.

[0024] Figure 3 A flowchart of a method for denoising the original operational behavior dataset and the resulting operational behavior feature set is shown.

[0025] Figure 4 A flowchart illustrating a method for determining a user's personalized operating pattern is shown.

[0026] Figure 5 A flowchart of a method for dynamically calculating the aging degree and remaining life prediction of each button is shown.

[0027] Figure 6 A flowchart of a method for determining the load distribution of each button is shown;

[0028] Figure 7 A flowchart illustrating a method for dynamically adjusting the load of each button is shown.

[0029] Figure 8 A unit block diagram of a load adjustment device for automotive buttons according to an embodiment of this application is shown;

[0030] Figure 9 This is a block diagram of an electronic device for load adjustment of automotive buttons, according to an exemplary embodiment. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0032] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to limit the application. The singular forms “a,” “said,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0033] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0034] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0035] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0036] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0037] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0038] The optional embodiments of this application are described in detail below with reference to the accompanying drawings.

[0039] The embodiments provided in this application are embodiments of a method for adjusting the load of automotive buttons.

[0040] The following is combined Figure 1 The embodiments of this application will be described in detail.

[0041] Figure 1 A flowchart of a method for adjusting the load of automotive buttons is shown, such as... Figure 1 As shown, the procedure includes steps S101 to S104.

[0042] Step S101: Real-time data collection of user operation data on the car dashboard buttons.

[0043] For example, sensors can be used to collect real-time data on user actions on car dashboard buttons. This data includes multi-dimensional information such as button pressure distribution range, operation periodicity, and duration fluctuations.

[0044] Step S102: Construct a user's operation behavior feature set based on the operation data, and perform personalized operation analysis based on the operation behavior feature set to determine the user's personalized operation mode.

[0045] Step S103: Dynamically calculate the aging degree value and remaining life prediction value of each button according to the personalized operation mode, and determine the load distribution of each button according to the aging degree value and remaining life prediction value of each button.

[0046] Step S104: Based on real-time monitoring of the load distribution, dynamically adjust the load of each button.

[0047] The method provided in this application collects real-time user operation data on car dashboard buttons and constructs a user operation behavior feature set based on this data. This method enables in-depth analysis of users' personalized operation patterns. Based on this, it dynamically calculates the aging degree and remaining lifespan prediction of each button according to the personalized operation pattern. This allows the system to accurately assess the specific wear condition of each button, thereby achieving effective monitoring of the button load distribution. Ultimately, dynamic adjustments based on the load distribution effectively extend the button's lifespan, reduce the risk of premature failure due to overuse, improve user experience, and reduce maintenance costs.

[0048] In the above embodiments, the operation behavior feature set is a set of data reflecting user operation habits obtained by denoising operation data, and the personalized operation mode is the unique operation mode of each user. By processing the operation data in a series of ways, the user's personalized operation mode is obtained, which facilitates the accurate capture of the user's actual usage and further refines a series of user habits, thereby providing a basis for key wear assessment and load distribution.

[0049] Furthermore, the parameters used to assess the button's usage status consist of two parts: an aging degree value and a remaining lifespan prediction value. The aging degree value reflects the degree of physical wear and tear on the buttons due to long-term use and is a crucial parameter for assessing the buttons' health. The remaining lifespan prediction value helps identify which buttons are likely to fail soon, allowing for proactive maintenance or functional reassignment to extend the overall module's lifespan. This application can determine the button load under the current layout based on a comprehensive consideration of the aging degree value and the remaining lifespan prediction value, enabling dynamic analysis and real-time adjustments.

[0050] In this embodiment of the application, the user's operation data on the car dashboard buttons can be collected in real time in the following manner, and then the user's operation behavior feature set can be constructed in the following manner.

[0051] Figure 2 A flowchart illustrating a method for collecting operational data and constructing an operational behavior feature set is shown, as follows: Figure 2 As shown, the procedure includes steps S201 to S204.

[0052] Step S201: Real-time acquisition of multi-dimensional data including key pressure distribution range, operation periodic data, and duration fluctuation data to construct the original operation behavior dataset.

[0053] Step S202: Denoise the original operation behavior dataset to obtain the denoised operation behavior feature set.

[0054] Step S203: Extract feature values ​​of key pressure distribution range and operation periodic data from the denoised operation behavior feature set, and perform distribution analysis on the feature values ​​to obtain the mean and standard deviation of the feature values.

[0055] Step S204: In the denoised operation behavior feature set, feature values ​​that deviate from the mean by more than a preset multiple of the standard deviation are screened out to form the user's operation behavior feature set.

[0056] When collecting user operation data, this invention employs multi-dimensional data, including key pressure distribution ranges, operation periodicity data, and duration fluctuation data, ensuring the comprehensiveness and accuracy of the original operation behavior dataset. By denoising the original dataset, removing outliers, and extracting the mean and standard deviation of feature values, the quality of data analysis is further improved. This meticulous data processing method guarantees the reliability of subsequent analysis results, making the determination of personalized operation modes more closely reflect the user's actual usage.

[0057] In some embodiments, a set of operational behavior features is constructed using key pressure distribution range, operation periodicity data, and duration fluctuation data. Key pressure distribution range records the range of pressure applied by the user when pressing a key. For example, the pressure applied by a user pressing a dashboard key may vary between 2 and 8 Newtons over a period of time. This data helps to understand the differences in key pressure applied by different users or in different scenarios. By analyzing the key pressure distribution range, the wear and tear on the key due to prolonged exposure to varying degrees of pressure can be assessed, thus providing a basis for predicting the aging degree of the key. Operation periodicity data refers to the time interval or frequency of user key presses, such as the number of presses per minute. Assuming a normal user operation frequency ranges from 5 to 15 times per minute, but may reach 20 times per minute at certain times, this data can reveal user operating habits and whether there are abnormally high-frequency operating behaviors. By analyzing operation periodicity, high-load usage patterns that may lead to accelerated key aging can be identified, and measures can be taken to adjust and extend key life. Duration fluctuation data describes the variation in the duration of each key press, i.e., the fluctuation in the length of time from key press to release. For example, the duration of several consecutive key presses might be 0.2 seconds, 0.5 seconds, or 0.1 seconds. This data can help understand changes in the speed and manner of key presses in different situations. Analyzing the fluctuations in duration can help detect additional wear risks caused by fast or slow operations, and optimize key design or usage strategies accordingly.

[0058] In some other embodiments, in addition to key pressure distribution range, operation periodicity data, and duration fluctuation data, the following data types can be considered to construct a more comprehensive operation behavior dataset. For example, finger contact area, environmental factor data, user biometric data, operation sequence and combination preferences, visual feedback and response time, and user location information can also serve as the data foundation for constructing the operation behavior dataset.

[0059] For example, among the data that can be considered, finger contact area can reflect how users press buttons, and different contact areas may cause different wear patterns on the buttons. Analyzing finger contact area can help optimize button design, such as adjusting the button surface material or shape to suit user habits and reduce wear. Environmental factor data includes data on external environmental conditions such as temperature and humidity, which helps understand the differences in the aging rate of button materials under different environments. For example, in humid environments, some button materials may age faster or corrode. Understanding these effects can help develop more durable button materials or take protective measures. User biometric data can be used in human-computer interaction research to analyze how a user's emotional state or fatigue level affects their button operation. This helps identify situations that may lead to misoperation or overuse, and adjust the interface design accordingly or provide timely reminders. Operation sequence and combination preferences refer to the order in which users press buttons and the commonly used button combinations. For example, some users may be accustomed to pressing the volume up button first and then the navigation key. Understanding these preferences can help optimize button layout or preset function combinations, improving operational efficiency and convenience. Visual feedback and response time measure the time from when a user presses a button to when the system responds, as well as the quality of the visual or auditory feedback. This data can be used to evaluate whether the system's response speed meets user expectations, thereby optimizing the user experience. Fast and accurate feedback enhances the user's sense of control and reduces frustration caused by delays. User location information can be used to analyze differences in usage habits across different geographical locations. For example, urban drivers and rural drivers may have different button usage patterns. Such insights can be used to specifically improve product design to better meet the needs of users in different regions.

[0060] In the above embodiments, the original operation behavior dataset is denoised, for example, in the following manner.

[0061] Figure 3 This diagram illustrates a method for denoising the original operational behavior dataset, resulting in a denoised operational behavior feature set. Figure 3 As shown, the procedure includes steps S301 to S303.

[0062] Step S301: In the original operation behavior dataset, data points with pressure values ​​exceeding a preset pressure threshold and / or frequency values ​​exceeding a preset frequency threshold are filtered out to obtain the filtered operation behavior dataset.

[0063] Step S302: For the filtered operational behavior dataset, the duration volatility data is processed using a time series smoothing tool, and the duration volatility data is smoothed using a sliding window method to obtain the smoothed volatility series.

[0064] Step S303: Based on the deviation between the original sequence represented by the duration volatility data and the smoothed volatility sequence, data points with abnormal fluctuations are filtered out from the filtered operational behavior dataset to serve as the denoised operational behavior feature set.

[0065] In this embodiment, to further improve data quality, when denoising the original operational behavior dataset, pressure values ​​and frequency values ​​exceeding a preset threshold are first filtered out. Then, a time series smoothing tool is used to smooth the duration fluctuations. Finally, data points with abnormal fluctuations are filtered out based on the deviation values. This method effectively reduces the impact of data noise on the analysis results, improves the accuracy and stability of the operational behavior feature set, and provides high-quality data support for subsequent personalized analysis.

[0066] The method provided in this application collects multi-dimensional data on user operation of car dashboard buttons using sensors, including button pressure distribution range, operation periodicity, and duration fluctuations, to construct an original operation behavior dataset. The pressure and frequency values ​​in the dataset are then filtered using preset range thresholds. If a pressure or frequency value exceeds the preset range threshold, it is marked as an abnormal data point, resulting in a pre-filtered operation behavior dataset. For the pre-filtered operation behavior dataset, a time series smoothing tool is used to process the duration fluctuation data. A sliding window method is used to smooth the data, obtaining a smoothed fluctuation sequence. The deviation between the smoothed data sequence and the original data sequence is used to determine if there are any abnormal fluctuation points, resulting in a denoised operation behavior feature set. Feature values ​​of button pressure distribution range and operation periodicity are extracted from the denoised operation behavior feature set. Statistical tools are used to perform distribution analysis on the feature values, obtaining the mean and standard deviation. If a feature value deviates from the mean by more than a preset multiple of the standard deviation, it is marked as a potential abnormal feature, thus determining the cleaned subset of user behavior features.

[0067] For example, in the scenario of collecting and analyzing data on button operation behavior in a car dashboard, sensors can record multi-dimensional data of user operations in real time, such as button pressure, operation frequency, and duration fluctuations. Taking the button pressure distribution range as an example, assuming the sensor collects that the pressure value of a user pressing a dashboard button within a certain time period is between 2 and 8 Newtons, while the preset normal pressure range threshold is 3 to 7 Newtons, then pressure values ​​exceeding this range will be marked as abnormal data points. This filtering method helps to initially eliminate obviously unreasonable data, ensuring the accuracy of subsequent analysis.

[0068] In one possible implementation, for processing periodic operation data, assuming the normal range for user operation frequency is 5 to 15 times per minute, if the frequency reaches 20 times per minute within a certain period, it will be marked as abnormal. This method can effectively identify data deviations caused by possible user errors or equipment malfunctions, ensuring the reliability of the dataset.

[0069] In some specific embodiments, time series smoothing tools can be used to process duration fluctuation data using a sliding window approach. For example, assuming the original data shows fluctuations in key press duration with values ​​of 0.2, 0.5, 0.1, 0.6, and 0.3 seconds for five consecutive time points, setting the window size to three time points may result in a more stable sequence after smoothing, such as 0.26, 0.4, and 0.33 seconds. By comparing the deviation between the smoothed data and the original data, if a deviation exceeds a preset threshold, such as 0.2 seconds, it is marked as an abnormal fluctuation point. This smoothing process effectively reduces the interference of data noise on subsequent analysis and improves the accuracy of feature extraction. It should be noted that when extracting key pressure distribution range and operation periodicity feature values ​​from the denoised operation behavior feature set, statistical tools can be used for distribution analysis. Assuming the extracted pressure feature value has a mean of 5 Newtons and a standard deviation of 1 Newton, if a user's pressure feature value is 8 Newtons, deviating from the mean by more than twice the standard deviation, it is marked as a potential abnormal feature. This method can further filter out anomalous data that may affect model training, forming a cleaned subset of user behavior features.

[0070] Preferably, each step of the above method revolves around the core characteristics of user behavior, ensuring that the analysis results are closely related to actual business needs. For example, marking outlier data points not only improves data quality but also provides more reliable basic data for subsequent user behavior modeling, thereby optimizing dashboard design or enhancing user experience.

[0071] In one embodiment, the potential patterns in user operating habits can be further analyzed from a subset of user behavior characteristics after cleaning. For example, if it is found that a certain type of user tends to operate buttons with higher pressure, it may indicate that the dashboard button design needs to adjust the tactile feedback. Such analysis results have direct guiding significance for product improvement.

[0072] In the above embodiments, through the collection, filtering, smoothing and feature extraction of multi-dimensional data, the entire process forms a complete closed loop. From raw data to cleaned feature sets, each step lays the foundation for the final user behavior analysis, while significantly improving the scientificity and practicality of data processing.

[0073] In some embodiments, a user's personalized operating mode can be determined in the following ways.

[0074] Figure 4 A flowchart illustrating a method for determining a user's personalized operating pattern is shown, such as... Figure 4 As shown, the procedure includes steps S401 to S402.

[0075] Step S401: Based on the user's operation behavior feature set, a clustering algorithm is used to classify the finger contact area and key combination preference of the user under different operation scenarios, and personalized features are extracted with reference to the classification results.

[0076] Step S402: Determine the user's personalized operation mode by referring to the mapping relationship between personalized features and personalized operation modes.

[0077] In this embodiment, based on the user's operation behavior feature set, a clustering algorithm can be used to classify the user's finger contact area and key combination preference under different operation scenarios, and personalized features can be extracted with reference to the classification results.

[0078] For example, based on the cleaned user behavior feature set, clustering algorithms can be used to classify finger contact area and key combination preferences to identify user behavior patterns in different scenarios. This classification process allows for the extraction of finger contact area variation data and key combination preferences associated with specific scenarios from multi-dimensional data, thereby determining the user's personalized characteristics. Based on this, when determining the user's personalized operation pattern, the mapping relationship between the previously extracted personalized features and known personalized operation patterns is directly used. For instance, in the analysis of car dashboard button operation behavior, assuming there are significant differences in user contact area data between urban congestion and highway cruising scenarios, clustering algorithms can transform these differences into specific user behavior patterns, such as an average contact area of ​​2 square centimeters in urban scenarios and 3 square centimeters in highway scenarios. Such classification helps reveal the impact of different driving scenarios on finger contact area and infers corresponding personalized operation patterns. Furthermore, when it comes to specific operation time distribution and force change rate, personalized features obtained from the clustering process can be directly utilized instead of further time-series partitioning or smoothing. For example, if a user's force change rate is faster during the morning rush hour, with an average adjustment range of 1 Newton per minute, while it is slower in the evening, with an adjustment range of only 0.5 Newtons, this information is already included in the personalized features and can be used to build personalized operating patterns.

[0079] In the embodiments described above, clustering algorithms are used to directly extract personalized features from the user's behavioral feature set. The personalized operation mode is then determined based on the mapping relationship between these features and the personalized operation mode, ensuring the directness and accuracy of the process from data analysis to mode determination. This provides a solid foundation for subsequent function allocation optimization. This method not only simplifies the data analysis process but also improves the accuracy and practicality of the final personalized operation mode.

[0080] In determining a user's personalized operating pattern, the mapping relationship refers to the association rules between personalized features and specific operating patterns. These rules are derived by analyzing user behavior data. First, based on collected sets of operational behavior features, such as key pressure distribution ranges, operation periodicity, and duration fluctuations, a clustering algorithm is used to classify finger contact area and key combination preferences in different scenarios, extracting personalized features including operation time distribution and pressure change rate. Further, in some pre-processing steps, a mapping relationship is constructed based on the correspondence between these personalized features and known personalized operating patterns. This process is typically completed by a trained machine learning model, which uses historical data analysis to identify which feature combinations correspond to which operating patterns, thus establishing the mapping relationship. Based on this, in practical applications, when new user behavior data is input into the system, the system will automatically identify and determine the user's personalized operating pattern based on the previously constructed mapping relationship. This allows for dynamic adjustment of key function allocation and load management strategies according to the user's specific usage habits, optimizing user experience and extending key lifespan.

[0081] Figure 5 A flowchart illustrating a method for dynamically calculating the aging degree and remaining lifespan prediction of each button is shown, as follows: Figure 5 As shown, the procedure includes steps S501 to S504.

[0082] Step S501: Based on the personalized operation mode, the pressure range is divided and the frequency fluctuation range is layered according to the key pressure distribution and operation cycle. The pressure accumulation data of each key in each operation cycle is obtained as the layered pressure distribution combination.

[0083] Step S502: Based on the duration fluctuation data and the differences in operating modes, the pressure distribution combination is divided into time series to obtain the wear state dynamic data in each time period, which is used as the wear feature group.

[0084] Step S503: If the key operation frequency characterized by the wear feature group in the target time period exceeds the preset frequency fluctuation range threshold, the wear state dynamic data in the target time period is corrected, key position distribution data is extracted from the corrected data, and feature subsets that conform to the wear state are extracted from the key position distribution data.

[0085] The target time period refers to any one or more time periods that meet the criteria.

[0086] Step S504: Use regression analysis tools to predict and calculate the feature subset to obtain the aging degree value of each button under the pressure accumulation data.

[0087] Step S505: Determine the predicted remaining lifespan of each button based on its design lifespan and aging degree.

[0088] In this embodiment, based on personalized operation modes, the pressure range and frequency fluctuation range are layered according to the key pressure distribution and operation cycle. The cumulative pressure data of each key in each operation cycle is obtained as a layered pressure distribution combination. For example, in the scenario of analyzing the operation of car dashboard keys, the pressure distribution of keys in different operation cycles can be explored from the user's daily driving habits. Assume that the key pressure accumulates higher during weekday morning and evening rush hours due to frequent operation, while it is more stable on weekends. The pressure range can be divided into three levels: low, medium, and high. For example, low pressure is 0-2 Newtons, medium pressure is 2-5 Newtons, and high pressure is above 5 Newtons. Combined with the operation cycle, the cumulative pressure data of each key over a day is obtained. For example, the cumulative pressure of a certain key during the morning rush hour is 30 Newtons, while on the weekend it is only 10 Newtons. This layering method can clearly reflect the impact of user operation habits on keys.

[0089] In this embodiment, the pressure distribution combination is time-series divided according to the duration fluctuation data and differences in operating modes to obtain dynamic data on wear status within each time period, forming wear feature groups. For example, using time series processing tools, a day's driving data is divided into hourly segments. From 7-9 AM, driving is likely dominated by rapid adjustments, with high button usage frequency and short durations. From 8-10 PM, driving is dominated by stable operations with longer durations. This allows for the acquisition of dynamic wear status data within each time period; for example, a button may wear faster during the morning rush hour and slower in the evening. This dynamic data helps identify the force variation patterns of buttons in different time periods.

[0090] In some embodiments, if the frequency of key presses within a certain time period in a wear feature group exceeds a preset frequency fluctuation range threshold, the dynamic wear status data for that target time period can be corrected. For example, if the normal operating frequency range is 1-2 times per minute, but the data for a certain period reaches 5 times per minute, then these data need to be corrected. The corrected data can more accurately reflect the actual usage of the keys, and a subset of features that conform to the wear status can be extracted from it.

[0091] Furthermore, regression analysis tools can be used to predict and calculate the aging degree of each button under the accumulated pressure data. For example, by combining the accumulated pressure data and the frequency of operation, the aging degree of a certain button under the current usage intensity can be predicted. Assuming that the accumulated pressure of a certain button is 100 Newtons, its remaining lifespan is predicted to be 6 months.

[0092] In this embodiment, the pressure distribution combination is essentially a set of accumulated operational data for the buttons within different pressure ranges. This data is used to assess the wear and aging of the buttons, thereby predicting their remaining lifespan. The entire analysis process revolves around the wear and aging of automotive dashboard buttons, ensuring the results are relevant to actual driving scenarios. From pressure distribution stratification to time-series partitioning, data correction, and lifespan prediction, the entire process forms a complete chain, providing reliable support for button durability analysis. This meticulous approach is of significant value for subsequent product improvements.

[0093] In some embodiments, the load distribution of each button can be determined by applying the aging degree value and the remaining life prediction value of each button as follows.

[0094] Figure 6 A flowchart illustrating a method for determining the load distribution of each button is shown, as follows: Figure 6 As shown, the procedure includes steps S601 to S602.

[0095] Step S601: Calculate the lifespan ratio of each button according to the aging degree value and the predicted remaining lifespan value of each button, and extract the distribution of each button from the lifespan ratio of each button.

[0096] Step S602: Combining the material durability data and distribution of each button, a comparative analysis tool is used to determine the load distribution of each button.

[0097] In this embodiment, the remaining lifespan ratio of each button is calculated based on its aging level and predicted remaining lifespan. The distribution of each button is then extracted from these ratios. For example, when analyzing button aging data and predicted remaining lifespan, a preset calculation rule can be used to compare the current usage data of the buttons with standard lifespan data. Assuming a button's expected lifespan is 1 million presses, and it has already been used 800,000 times, the remaining lifespan ratio is 20%. This comparison method intuitively reflects the current state data of the buttons, providing a basis for subsequent analysis.

[0098] In some embodiments, the load distribution of each button can be determined by using a comparative analysis tool, which combines the material durability data and distribution of each button.

[0099] As a feasible implementation, when extracting the distribution of each button from the lifespan ratio, in-depth analysis can be conducted by combining the button's material durability data. Assuming that the material durability of different buttons on a car dashboard varies, frequently used buttons like button A may use a high-durability material, while peripheral buttons like button B may use a common material. Through comparative analysis tools, it can be found that although button A is used frequently, its lifespan ratio is still higher than button B due to its material advantage. This analysis helps identify potential problems in the load distribution.

[0100] In this embodiment, the remaining lifespan ratio is calculated based on the aging level of the buttons and the predicted remaining lifespan, and the load distribution is determined in conjunction with material durability data. This method allows the system to understand the status of each button in real time and promptly identify potential problem areas. By applying comparative analysis tools, the load status of each button can be judged more scientifically and reasonably, providing a reliable basis for subsequent load adjustments and ensuring the stable operation of the entire button system.

[0101] Figure 7 A flowchart illustrating a method for dynamically adjusting the load of each button is shown, such as... Figure 7 As shown, the procedure includes steps S701 to S702.

[0102] Step S701: Obtain the position information of each button according to the load distribution, and perform threshold monitoring on each button for the life margin ratio.

[0103] The remaining life ratio is determined based on the aging degree and the predicted remaining life.

[0104] Step S702: If the first button is detected to have a lifespan margin ratio lower than the preset margin ratio threshold and the first button meets the preset load allocation rules, the function allocation optimization logic is invoked, the second button is selected from the buttons, and the functions of the first button and the second button are swapped.

[0105] The preset load distribution rules include ensuring that the first button and a specified number of adjacent buttons each satisfy a lifespan margin ratio deviation greater than a preset deviation threshold.

[0106] In this embodiment, based on the load distribution, the corresponding button position information is obtained. For example, if the remaining lifespan of a button is lower than a preset threshold, a load imbalance flag is generated for subsequent adjustment judgment. For instance, assuming the C button on a car dashboard is frequently used by users and its remaining lifespan is only 10%, the system will mark this button as having an unbalanced load. This flag provides a clear direction for subsequent adjustment judgment and helps extend the overall service life of the device.

[0107] In some embodiments, based on the load imbalance indicator, the identification information of the target key is extracted. Using a preset load distribution rule, it is determined whether a load adjustment request signal should be generated, and the specific proportion of load transfer is determined. For example, when the margin ratio of a certain key is less than 15% and the margin ratio of adjacent keys is greater than 30%, an adjustment signal needs to be generated. For instance, if the margin ratio of key C is 10%, while the margin ratio of the adjacent key D is 35%, the system will generate a signal suggesting that some of the operation load be transferred to key D. This method effectively balances the load distribution among the keys.

[0108] Preferably, when determining the specific proportion of load transfer, it can be reasonably allocated based on the difference in the margin ratio between the buttons. For example, if the difference in the margin ratio between the C button and the D button is 25%, the system may suggest transferring 20% ​​of the operating load to the D button to avoid over-adjustment leading to new imbalances.

[0109] For example, in processing button usage data, predefined usage data records can be understood as a long-term accumulated database containing information such as the number of times each button is pressed and its time distribution. Suppose there are 10 frequently used buttons on a car dashboard. Data records show that button A is pressed 500 times a day, while button B is pressed only 50 times. This frequency difference directly reflects the frequency of function presses. Simultaneously, the importance level of a function can be categorized by the type of function associated with the button. For instance, button A is associated with a core input function and has a high importance level, while button B is only an auxiliary function and has a low importance level.

[0110] As a feasible implementation, when extracting the remaining percentage data from the button life monitoring module, we can assume that button A has a remaining percentage of 30%, while button B has 80%, indicating that button A's lifespan is consumed faster. For the classification of high-load and low-load buttons, those with a remaining percentage below 50% can be grouped into the high-load group, and those above 70% into the low-load group, thus forming an initial mapping table that clearly shows the load distribution.

[0111] As a feasible implementation, the position information of each button is obtained based on the load distribution, and a threshold monitoring of the remaining lifespan ratio of each button is performed. For example, if the remaining lifespan ratio of button A is 30%, which is lower than the preset threshold of 35%, a signal is triggered, indicating that adjustment is needed. Considering its high functional importance, frequency of 500 times / day, and its central location on the dashboard, it is determined that the set of functions to be transferred may be some secondary input tasks.

[0112] In some embodiments, if the remaining lifespan ratio of button A is detected to be lower than a preset remaining lifespan ratio threshold and a preset load allocation rule is met, the function allocation optimization logic is invoked. Specifically, it is assumed that button A and a specified number of adjacent buttons each satisfy a remaining lifespan ratio deviation greater than a preset deviation threshold. In this case, a preliminary function allocation adjustment scheme can be generated, transferring some functions of button A to button B. For example, tasks with a frequency of 100 times / day on button A can be transferred to button B to reduce the load on button A.

[0113] Preferably, in the low-load key matching calculation, it is assumed that the margin ratio of key B is 80%, and its position is adjacent to key A, with a proximity score of 90, thus meeting the transfer conditions. In this case, the system will confirm that the transfer path is reasonable and ultimately form the adjusted function allocation result. For example, after the transfer, the frequency of key A drops to 400 times / day, still maintaining a high-importance function, while the frequency of key B increases to 150 times / day, still within an acceptable range.

[0114] In this embodiment, the verification process of the optimized logic module can focus on the balance between functional importance and frequency. Assuming that after the above adjustments, the frequency of button A drops to 400 times / day while still maintaining a high-importance function, while the frequency of button B increases to 150 times / day, still within an acceptable range, then the transfer path is confirmed to be reasonable, ultimately resulting in the adjusted function allocation. This design not only extends the lifespan of high-load buttons but also improves the overall stability of the device, providing users with a smoother operating experience. For example, in practical applications, if a central button on a car dashboard ages rapidly due to frequent use, transferring some tasks to edge buttons using the above method can not only prevent premature failure of a single button but also optimize user operating habits and reduce the risk of misoperation due to button malfunction. This multi-faceted load management approach fully demonstrates the practical value and flexibility of the solution.

[0115] In this embodiment, the main purpose of load adjustment is to extend the overall lifespan of the buttons by balancing their usage. Based on this design concept, in addition to the function swapping described above, this application also considers the following methods for load adjustment.

[0116] Functional distribution for buttons can be implemented, similar to the design of a car dashboard. Suppose button A, due to frequent use, has a lifespan below a preset threshold, while buttons B and C have a longer lifespan. To extend the lifespan of button A, the system can distribute some of its functions, such as volume control, to buttons B and C. For example, the volume increase function, originally handled by button A, can be moved to button B, and the volume decrease function to button C. This not only reduces the workload on button A but also ensures the integrity of the overall functionality and a consistent user experience.

[0117] Dynamic load balancing involves the system monitoring the usage of each button in real time and dynamically adjusting the button's function allocation based on the load distribution. For example, if the usage frequency of buttons A and B increases significantly within a certain period, the system can temporarily allocate some functions to less frequently used buttons such as C and D using an algorithm. Specifically, when the usage frequency of button A exceeds a set threshold, the system automatically transfers some non-critical operations, such as adjusting the air conditioning temperature, to button C. Once the load returns to normal, the original settings are restored. This method effectively prevents premature button failure due to short-term high load usage.

[0118] Preventative load balancing, such as to prevent premature failure of buttons before they reach critical usage levels, allows the system to perform load balancing in advance based on predictive models. For example, if the system predicts that button A's usage frequency will increase significantly in the future and its remaining lifespan is close to a preset threshold, the system can preemptively transfer some functions to other buttons. For instance, before button A's remaining lifespan drops to 20%, the system can transfer certain high-frequency operations, such as navigation input, to button B, thereby extending button A's lifespan while maintaining normal functionality.

[0119] Function priority adjustments can be made, such as reallocating function priorities based on button importance and usage frequency to reduce the burden on frequently used but non-critical functions. For example, non-critical functions like backlight adjustment can be moved from frequently used buttons like the A button to less frequently used buttons like the E button. Critical functions, such as the start / stop button, can maintain their original configuration or be moved to more durable buttons. In practice, the system can automatically adjust these function allocations through the user settings interface or background algorithms, ensuring that critical functions are not affected while reducing the pressure on specific buttons from non-critical functions.

[0120] User behavior guidance, such as through user interface prompts or suggestions, can encourage users to change their operating habits and reduce reliance on specific buttons. For example, the system can display prompts on the screen suggesting users try using other buttons to complete certain operations, or provide shortcuts to reduce the burden of button usage. Specifically, when the system detects that button A is used too frequently, it can display a prompt on the screen: "You can use the touchscreen to adjust the air conditioning temperature to reduce the burden on physical buttons." This guidance method not only extends the lifespan of buttons but also improves the user experience.

[0121] Key combination optimization, such as designing new key combinations or shortcuts, reduces the frequency of using individual keys. For example, introducing double-clicking or multi-key combinations to perform certain functions. Specifically, a key A that previously required frequent pressing can now be operated by simultaneously pressing keys B and C. For instance, adjusting the volume of the car audio system can be done by pressing keys B and C simultaneously, instead of using key A alone. This not only reduces wear and tear on key A but also provides users with a new operating method, enhancing the system's flexibility.

[0122] Regularly rotating functions, such as periodically switching buttons, ensure more even wear on all buttons. For example, the system automatically swaps the functions of buttons A and B at regular intervals. Specifically, the system automatically switches the functions of buttons A and B on the first day of each month. This prevents excessive wear from concentrating on the same button even if a function is used frequently. For instance, if button A was originally used for navigation input and button B for audio control, after the rotation, button A will be used for audio control and button B for navigation input, thus achieving a more even distribution of button wear.

[0123] In this embodiment, based on real-time monitoring of load distribution, the buttons are dynamically adjusted. Especially for buttons with low remaining lifespan, function allocation optimization logic transfers some functions to adjacent, less loaded buttons, effectively balancing the load distribution among the buttons. This strategy not only prevents premature button failure but also fully utilizes button resources, extending the overall device lifespan. Furthermore, by setting reasonable load allocation rules, optimal results are ensured with each adjustment, thereby improving user experience and reducing maintenance costs.

[0124] This application also provides apparatus embodiments that follow the above embodiments, for implementing the method steps of the above embodiments. The interpretation of the same names is the same as that of the above embodiments, and they have the same technical effects as those of the above embodiments, so they will not be repeated here.

[0125] like Figure 8As shown, this application provides a load adjustment device 800 for automotive buttons, comprising:

[0126] The data acquisition unit 801 is used to collect user operation data on the buttons of the car dashboard in real time, and to construct a user operation behavior feature set based on the operation data.

[0127] The determining unit 802 is used to perform personalized operation analysis based on the operation behavior feature set to determine the user's personalized operation mode. It is also used to dynamically calculate the aging degree value and remaining lifespan prediction value of each button based on the personalized operation mode. Furthermore, it is used to determine the load distribution of each button according to the aging degree value and remaining lifespan prediction value, and to dynamically adjust the load of each button based on real-time monitoring of the load distribution.

[0128] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0129] Figure 9 This is a block diagram of an electronic device 900 for load adjustment of automotive buttons, according to an exemplary embodiment.

[0130] like Figure 9 As shown, one embodiment of this application provides an electronic device 900. The electronic device 900 includes a memory 901, a processor 902, and an input / output (I / O) interface 903. The memory 901 stores instructions. The processor 902 is used to execute the method for adjusting the load of automotive buttons according to embodiments of this application by calling the instructions stored in the memory 901. The processor 902 is connected to both the memory 901 and the I / O interface 903, for example, via a bus system and / or other forms of connection mechanisms (not shown). The memory 901 can be used to store programs and data, including the program for the method of adjusting the load of automotive buttons according to embodiments of this application. The processor 902 executes various functional applications and data processing of the electronic device 900 by running the program stored in the memory 901.

[0131] In this embodiment, the processor 902 can be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field Programmable Gate Array (FPGA), Programmable Logic Array (PLA). The processor 902 can be one or a combination of several of the following: Central Processing Unit (CPU) or other processing units with data processing capabilities and / or instruction execution capabilities.

[0132] The memory 901 in this embodiment may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD).

[0133] In this embodiment, the I / O interface 903 can be used to receive input instructions (such as numeric or character information, and to generate key signal inputs related to user settings and function control of the electronic device 900), and can also output various information (such as images or sounds) to the outside. In this embodiment, the I / O interface 903 may include one or more of the following: a physical keyboard, function keys (such as volume control keys, power buttons, etc.), a mouse, a joystick, a trackball, a microphone, a speaker, and a touch panel.

[0134] In some embodiments, this application provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, perform any of the methods described above.

[0135] In some embodiments, this application provides a computer program product comprising a computer program that, when executed by a processor, performs any of the methods described above.

[0136] Although the operations are described in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order or serial order shown, or requiring all of the operations shown to obtain the desired result. In certain environments, multitasking and parallel processing may be advantageous.

[0137] The methods, apparatus, devices, and storage media of this application can be implemented using standard programming techniques, and various method steps can be implemented using rule-based logic or other logic. It should also be noted that the terms "apparatus" and "module" as used herein and in the claims are intended to include implementations using one or more lines of software code and / or hardware implementations and / or devices for receiving input.

[0138] Any step, operation, or procedure described herein may be performed or implemented using one or more hardware or software modules, either alone or in combination with other devices. In one embodiment, the software module is implemented using a computer program product comprising a computer-readable medium containing computer program code, which is executable by a computer processor to perform any or all of the described steps, operations, or procedures.

[0139] The foregoing description of implementations of this application has been provided for illustrative and descriptive purposes. The foregoing description is not exhaustive and is not intended to limit this application to the exact forms disclosed. Various modifications and variations may exist in accordance with the foregoing teachings, or may arise from practice of this application. These embodiments were chosen and described to illustrate the principles of this application and its practical application, enabling those skilled in the art to utilize this application in various implementations and modifications to suit the specific purpose of the concept.

[0140] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0141] It can be further understood that, unless otherwise specified, "connection" includes both direct connections where no other components exist between the two parties and indirect connections where other components exist between them.

[0142] It is further understood that although the operations are described in a specific order in the accompanying drawings in the embodiments of this application, this should not be construed as requiring these operations to be performed in the specific order or serial order shown, or requiring all the operations shown to be performed to obtain the desired result. In certain environments, multitasking and parallel processing may be advantageous.

[0143] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the field of this application that are not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0144] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

[0145] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for adjusting the load of automotive buttons, characterized in that, include: Real-time data collection of user input data on car dashboard buttons; Based on the operation data, a set of operation behavior features of the user is constructed, and personalized operation analysis is performed based on the set of operation behavior features to determine the user's personalized operation mode. The aging degree value and remaining life prediction value of each button are dynamically calculated according to the personalized operation mode, and the load distribution of each button is determined according to the aging degree value and remaining life prediction value of each button. Based on real-time monitoring of the load distribution, the load of each button is dynamically adjusted. The step of dynamically calculating the aging degree value and remaining lifespan prediction value of each button based on the personalized operation mode includes: Based on the personalized operation mode, the pressure range is divided and the frequency fluctuation range is layered according to the key pressure distribution and operation cycle. The pressure accumulation data of each key in each operation cycle is obtained as the layered pressure distribution combination. Based on the duration fluctuation data and the differences in operating modes, the pressure distribution combination is divided into time series to obtain the wear state dynamic data in each time period, which is used as the wear feature group. If the key operation frequency characterized by the wear feature group in the target time period exceeds the preset frequency fluctuation range threshold, the wear state dynamic data in the target time period is corrected, key position distribution data is extracted from the corrected data, and feature subsets that conform to the wear state are extracted from the key position distribution data. Regression analysis tools are used to predict and calculate the feature subset to obtain the aging degree values ​​of each button under the accumulated pressure data; Based on the design lifespan of each button and the aging degree value, the predicted remaining lifespan of each button is determined.

2. The method according to claim 1, characterized in that, The real-time acquisition of user operation data on the car dashboard buttons, and the construction of the user's operation behavior feature set based on the operation data, includes: Real-time acquisition of multi-dimensional data, including key pressure distribution range, operation periodic data, and duration fluctuation data, and construction of raw operation behavior dataset; The original operation behavior dataset is denoised to obtain a denoised operation behavior feature set. Feature values ​​of key pressure distribution range and operation periodic data are extracted from the denoised operation behavior feature set, and the distribution analysis of the feature values ​​is performed to obtain the mean and standard deviation of the feature values; In the denoised user behavior feature set, feature values ​​that deviate from the mean by more than a preset multiple of the standard deviation are filtered out to form the user's user behavior feature set.

3. The method according to claim 2, characterized in that, The denoising process of the original operation behavior dataset to obtain a denoised operation behavior feature set includes: Data points whose pressure values ​​exceed a preset pressure threshold and / or whose frequency values ​​exceed a preset frequency threshold are filtered out from the original operational behavior dataset to obtain the filtered operational behavior dataset. For the filtered operational behavior dataset, a time series smoothing tool is used to process the duration volatility data, and a sliding window method is used to perform smoothing calculations on the duration volatility data to obtain the smoothed volatility series; Based on the deviation between the original sequence characterized by the duration volatility data and the smoothed volatility sequence, data points with abnormal fluctuations are filtered out from the filtered operational behavior dataset to form a denoised operational behavior feature set.

4. The method according to claim 1, characterized in that, Determining the user's personalized operating mode includes: Based on the user's operation behavior feature set, a clustering algorithm is used to classify the finger contact area and key combination preference of the user under different operation scenarios, and personalized features are extracted with reference to the classification results. The user's personalized operation mode is determined by referring to the mapping relationship between personalized features and personalized operation modes.

5. The method according to claim 1, characterized in that, The step of determining the load distribution of each button based on its aging level and predicted remaining lifespan includes: Based on the aging degree value and remaining life prediction value of each button, calculate the life reserve ratio of each button, and extract the distribution of each button from the life reserve ratio of each button. By combining the material durability data and distribution of each button, a comparative analysis tool is used to determine the load distribution of each button.

6. The method according to claim 1 or 5, characterized in that, The method of dynamically adjusting the load on each button based on real-time monitoring of the load distribution includes: The position information of each button is obtained according to the load distribution, and the threshold monitoring of the remaining life ratio of each button is performed; wherein, the remaining life ratio is determined based on the aging degree value and the remaining life prediction value. If a first button is detected to have a lifespan margin ratio lower than a preset margin ratio threshold, and the first button meets a preset load allocation rule, then the function allocation optimization logic is invoked, a second button is selected from the buttons, and the functions of the first button and the second button are swapped. The preset load allocation rule includes that the first button and a specified number of adjacent buttons each satisfy a lifespan margin ratio deviation greater than a preset deviation threshold.

7. A load adjustment device for automotive buttons, characterized in that, For implementing the method as described in any one of claims 1 to 6, comprising: The data acquisition unit is used to collect user operation data on the car dashboard buttons in real time, and to construct the user's operation behavior feature set based on the operation data; The determining unit is configured to perform personalized operation analysis based on the operation behavior feature set to determine the user's personalized operation mode; dynamically calculate the aging degree value and remaining lifespan prediction value of each button based on the personalized operation mode; and determine the load distribution status of each button according to the aging degree value and remaining lifespan prediction value of each button, and dynamically adjust the load of each button based on real-time monitoring of the load distribution status.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the method described in any one of claims 1-6.

Images