Search

CN-120611450-B - Load adjusting method, device and equipment for automobile key and storage medium

CN120611450BCN 120611450 BCN120611450 BCN 120611450BCN-120611450-B

Abstract

The application relates to the field of automobile intelligence, and provides a load adjusting method, device and equipment for automobile keys and a storage medium. The method comprises the steps of collecting operation data of a user on keys of an automobile instrument panel in real time, constructing an operation behavior feature set of the user based on the operation data, conducting personalized operation analysis according to the operation behavior feature set, determining personalized operation modes of the user, dynamically calculating aging degree values and residual life predicted values of the keys according to the personalized operation modes, determining load distribution conditions of the keys according to the aging degree values and the residual life predicted values of the keys, and conducting load dynamic adjustment on the keys based on real-time monitoring of the load distribution conditions. The method provided by the application can effectively prolong the service life of the automobile key.

Inventors

  • Tan pan

Assignees

  • 苏州博亚科技有限公司

Dates

Publication Date
20260512
Application Date
20250515

Claims (9)

  1. 1. A load adjustment method for an automotive key, comprising: acquiring operation data of a user on keys of an automobile instrument panel in real time; constructing an operation behavior feature set of the user based on the operation data, and performing personalized operation analysis according to the operation behavior feature set to determine a personalized operation mode of the user; Dynamically calculating the aging degree value and the residual life predicted value of each key according to the personalized operation mode, and determining the load distribution condition of each key according to the aging degree value and the residual life predicted value of each key; Based on the real-time monitoring of the load distribution condition, carrying out load dynamic adjustment on each key; The dynamically calculating the aging degree value and the residual life prediction value of each key according to the personalized operation mode comprises the following steps: According to the personalized operation mode, layering processing is carried out on pressure interval division and frequency fluctuation ranges according to key pressure distribution and operation periods, and pressure accumulation data of each key under each operation period is obtained and used as a layered pressure distribution combination; According to the duration fluctuation data and the operation mode difference, carrying out time sequence division on the pressure distribution combination to obtain dynamic data of the abrasion state in each time period to be used as an abrasion characteristic group; If the key operation frequency represented by the abrasion feature set in the target time period exceeds a preset frequency fluctuation range threshold, correcting the abrasion state dynamic data in the target time period, extracting key position distribution data from the corrected data, and extracting a feature subset conforming to the abrasion state from the key position distribution data; performing predictive calculation on the feature subsets by adopting a regression analysis tool to obtain the aging degree value of each key under the pressure accumulation data; and determining a residual life prediction value of each key according to the key design life of each key and the aging degree value.
  2. 2. The method of claim 1, wherein the collecting operation data of the user on the dashboard buttons in real time and constructing the operation behavior feature set of the user based on the operation data comprises: acquiring multidimensional data comprising a key pressure distribution interval, operation periodic data and duration fluctuation data in real time and constructing an original operation behavior data set; denoising the original operation behavior data set to obtain a denoised operation behavior feature set; Respectively extracting key pressure distribution intervals and characteristic values of operation periodic data from the denoised operation behavior characteristic set, and carrying out distribution analysis on the characteristic values to obtain mean values and standard deviations of the characteristic values; And screening out characteristic values of which the deviation mean value exceeds the standard deviation preset multiple from the denoised operation behavior characteristic set to serve as the operation behavior characteristic set of the user.
  3. 3. The method according to claim 2, wherein denoising the original operational behavior data set to obtain a denoised operational behavior feature set comprises: Screening data points with pressure values exceeding a preset pressure threshold value and/or frequency values exceeding a preset frequency threshold value from the original operation behavior data set to obtain a screened operation behavior data set; Processing the duration fluctuation data by adopting a time sequence smoothing tool aiming at the screened operation behavior data set, and carrying out smoothing calculation on the duration fluctuation data in a sliding window mode to obtain a fluctuation sequence after the smoothing calculation; And screening data points with abnormal fluctuation in the screened operation behavior data set according to the deviation value between the original sequence represented by the duration fluctuation data and the fluctuation sequence after the smooth calculation, and taking the data points with abnormal fluctuation as a denoised operation behavior characteristic set.
  4. 4. The method of claim 1, wherein the determining the personalized operational mode of the user comprises: classifying finger contact areas and key combination preferences of users under different operation scene relativity by adopting a clustering algorithm based on the operation behavior feature set of the users, and extracting personalized features by referring to classification results; And determining the personalized operation mode of the user by referring to the mapping relation between the personalized features and the personalized operation mode.
  5. 5. The method of claim 1, wherein determining the load distribution of each key according to the age value and the predicted remaining life value of each key comprises: according to the aging degree value and the residual life prediction value of each key, respectively calculating the life allowance ratio of each key, and extracting the distribution condition of each key from the life allowance ratio of each key; And determining the load distribution condition of each key by adopting a comparison analysis tool in combination with the material durability data and the distribution condition of each key.
  6. 6. The method according to claim 1 or 5, wherein the dynamically adjusting the load of each key based on the real-time monitoring of the load distribution condition comprises: Acquiring position information of each key according to the load distribution condition, and carrying out threshold monitoring on each key aiming at a life margin ratio, wherein the life margin ratio is determined based on the aging degree value and the residual life predicted value; If a first key with the life margin ratio lower than a preset margin ratio threshold is detected, and the first key meets a preset load distribution rule, invoking a function distribution optimization logic, selecting a second key from the keys, and performing function exchange on the first key and the second key; The preset load distribution rule comprises that the deviation of the life allowance ratio between the first key and the appointed number of adjacent keys is larger than a preset deviation threshold.
  7. 7. A load regulation device for a car key, characterized in that it is adapted to implement a method according to any one of claims 1 to 6, comprising: the data acquisition unit is used for acquiring operation data of a user on keys of the automobile instrument panel in real time and constructing an operation behavior feature set of the user based on the operation data; The system comprises a key, a determining unit, a dynamic load adjusting unit and a load adjusting unit, wherein the key is used for carrying out a personalized operation analysis according to the operation behavior feature set to determine a personalized operation mode of a user, dynamically calculating an aging degree value and a residual life prediction value of each key according to the personalized operation mode, determining a load distribution condition of each key according to the aging degree value and the residual life prediction value of each key, and carrying out load dynamic adjustment on each key based on real-time monitoring of the load distribution condition.
  8. 8. An electronic device comprising a memory, a processor and a computer program stored on the memory, characterized in that the processor executes the computer program to implement the method of any one of claims 1-6.
  9. 9. A computer readable storage medium having stored thereon a computer program/instruction which, when executed by a processor, implements the method of any of claims 1-6.

Description

Load adjusting method, device and equipment for automobile key and storage medium Technical Field The application relates to the field of automobile intelligence, in particular to a load adjusting method, device and equipment for automobile keys and a storage medium. Background Along with the continuous promotion of the intelligent degree of car, car button plays vital role in intelligent car and daily driving as human-computer interaction's important interface. The reliability and durability of the system are directly related to the user experience and driving safety. However, the current method for managing the service life of the automobile key is limited to simple statistics of the number of times of use or periodic replacement, and lacks deep analysis of actual use habits of users, so that dynamic adjustment of key functions cannot be realized. The static management mode is difficult to adapt to the use difference of different users, so that part of keys are in premature failure, other key resources are not fully utilized, and the service life of the whole module is limited. Therefore, the application provides a load adjusting method, device and equipment for an automobile key and a storage medium, so as to solve one of the technical problems. Disclosure of Invention The application aims to provide a load adjusting method, device and equipment for an automobile key and a storage medium, which can solve at least one technical problem. The specific scheme is as follows: According to a first aspect of the present application, there is provided a load adjustment method for an automobile key, including: The method comprises the steps of collecting operation data of a user on keys of an automobile instrument panel in real time, constructing an operation behavior feature set of the user based on the operation data, carrying out personalized operation analysis according to the operation behavior feature set, determining a personalized operation mode of the user, dynamically calculating ageing degree values and residual life predicted values of the keys according to the personalized operation mode, determining load distribution conditions of the keys according to the ageing degree values and the residual life predicted values of the keys, and carrying out load dynamic adjustment on the keys based on real-time monitoring of the load distribution conditions. In one embodiment, the method comprises the steps of collecting operation data of a user on a button of an automobile instrument panel in real time, constructing an operation behavior feature set of the user based on the operation data, acquiring multidimensional data comprising a button pressure distribution interval, operation periodic data and duration fluctuation data in real time, constructing an original operation behavior data set, denoising the original operation behavior data set to obtain a denoised operation behavior feature set, respectively extracting characteristic values of the button pressure distribution interval and the operation periodic data from the denoised operation behavior feature set, carrying out distribution analysis on the characteristic values to obtain a mean value and a standard deviation of the characteristic values, and screening out the characteristic values, deviating from the mean value by more than a preset standard deviation, in the denoised operation behavior feature set to serve as the operation behavior feature set of the user. In one embodiment, denoising the original operation behavior data set to obtain a denoised operation behavior feature set, wherein the denoising processing is performed on the original operation behavior data set to obtain a filtered operation behavior data set by screening data points with pressure values exceeding a preset pressure threshold and/or frequency values exceeding a preset frequency threshold in the original operation behavior data set, processing the duration fluctuation data by adopting a time sequence smoothing tool aiming at the filtered operation behavior data set, and performing smoothing calculation on the duration fluctuation data in a sliding window mode to obtain a smoothed fluctuation sequence, and screening data points with abnormal fluctuation in the filtered operation behavior data set according to deviation values between the original sequence represented by the duration fluctuation data and the smoothed fluctuation sequence to serve as the denoised operation behavior feature set. In one embodiment, the method for determining the personalized operation mode of the user comprises classifying finger contact areas and key combination preferences under different operation scene correlations of the user by adopting a clustering algorithm based on the operation behavior feature set of the user, extracting personalized features according to classification results, and determining the personalized operation mode of the user according to mapping relations between the personal