Mobile phone screen display optimization method combined with scene monitoring

Abstract

The invention provides a mobile phone screen display optimization method combined with scene monitoring, and relates to the technical field of optical elements, and the method comprises the steps: calling a sensor array of a target mobile phone to carry out scene monitoring in a preset monitoring window; performing adjacent data interaction association analysis; performing same-type data centralized analysis on the scene monitoring data set sequence; using the scene monitoring data set value set as foreground data, using the interaction association scene monitoring data set as background data, and carrying out screen display parameter optimization screening in the display optimization space; and performing display optimization on the screen of the target mobile phone based on the target screen display optimization parameter. According to the method and the device, the technical problem that display optimization cannot adapt to environmental changes in real time due to lack of dynamic adjustment and intelligent automation mechanisms in the prior art can be solved, and the technical effects of intelligently and automatically adjusting the screen display parameters under various environmental conditions, improving the user experience and simplifying the operation process are achieved.

Description

Technical Field

[0001] The present application relates to the field of optical element technology, and in particular to a method for optimizing mobile phone screen display in combination with scene monitoring. Background Art

[0002] With the continuous advancement of technology, the screen display quality of portable devices such as smartphones has gradually become one of the key factors in user experience. The display effect of the screen directly affects the user's visual experience and comfort. In order to adapt to different usage scenarios, the optimization of screen display usually involves multiple factors, such as brightness, contrast, color temperature, etc. These factors will change with changes in lighting, ambient temperature and user needs.

[0003] At present, the existing technology mainly relies on static display optimization schemes, which respond to different environmental conditions through preset display parameters. However, this method has certain limitations. First, most of the existing technologies use fixed algorithms and preset values ​​for display optimization, and cannot be dynamically adjusted according to changes in the environment in real time. For example, when a user enters indoors from outdoors, the light conditions and ambient temperature change, and the brightness and color temperature of the screen display may not be able to adapt to the new conditions in time, thereby affecting the user's experience. Secondly, traditional display optimization methods usually rely on manual adjustment and lack an intelligent automatic adjustment mechanism, which requires users to perform frequent manual operations, increasing the complexity and inconvenience of the operation. In addition, most of the optimization algorithms in the prior art lack sufficient consideration of device characteristics and ignore the hardware differences of the device itself, resulting in large differences in optimization effects between devices of different brands and models.

[0004] In summary, the prior art has technical problems in that, due to the lack of dynamic adjustment and intelligent automation mechanisms, display optimization cannot adapt to environmental changes in real time, further affecting the user experience and operational convenience in different scenarios. Summary of the invention

[0005] The purpose of this application is to provide a mobile phone screen display optimization method combined with scene monitoring, so as to solve the technical problem in the prior art that the display optimization cannot adapt to environmental changes in real time due to the lack of dynamic adjustment and intelligent automation mechanism, further affecting the user's usage experience and operational convenience in different scenarios.

[0006] In view of the above problems, the present application provides a method for optimizing mobile phone screen display in combination with scene monitoring, including: calling the sensor array of the target mobile phone to perform scene monitoring in a preset monitoring window to obtain a scene monitoring data set sequence; performing interactive correlation analysis of adjacent data in sequence according to the sequence of scene monitoring data sets in the scene monitoring data set sequence to determine an interactively correlated scene monitoring data set; using the data type as an index, performing a centralized analysis of data of the same type on the scene monitoring data set sequence to determine a median set of scene monitoring data; using the median set of the scene monitoring data set as foreground data and the interactively correlated scene monitoring data set as background data, performing screen display parameter optimization screening in a display optimization space to determine target screen display optimization parameters; and optimizing the display of the screen of the target mobile phone based on the target screen display optimization parameters.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: The sensor array of the target mobile phone is called to perform scene monitoring in a preset monitoring window to obtain a scene monitoring data set sequence; the adjacent data interactive correlation analysis is performed in sequence according to the sequence of scene monitoring data sets in the scene monitoring data set sequence to determine the interactively correlated scene monitoring data set; the scene monitoring data set sequence is subjected to a centralized analysis of data of the same type with the data type as an index to determine the median set of the scene monitoring data; the scene monitoring data set median set is used as foreground data, and the interactively correlated scene monitoring data set is used as background data to perform screen display parameter optimization screening in a display optimization space to determine the target screen display optimization parameters; the screen of the target mobile phone is displayed optimized based on the target screen display optimization parameters, that is, by realizing the technical goal of dynamic display optimization adjustment based on real-time environmental data and device characteristics, the technical effect of intelligently and automatically adjusting the screen display parameters under various environmental conditions, improving the user experience and simplifying the operation process is achieved.

[0008] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0010] Figure 1 This is a flow chart of a method for optimizing mobile phone screen display in combination with scene monitoring in this application; Figure 2 This is a flow chart of determining an interactively associated scene monitoring data set in the mobile phone screen display optimization method combined with scene monitoring in this application. DETAILED DESCRIPTION

[0011] This application provides a method for optimizing mobile phone screen display combined with scene monitoring, which solves the technical problem in the prior art that the display optimization cannot adapt to environmental changes in real time due to the lack of dynamic adjustment and intelligent automation mechanism, further affecting the user experience and operation convenience in different scenarios. The technical goal of dynamic display optimization adjustment based on real-time environmental data and device characteristics is achieved, and the technical effect of intelligently and automatically adjusting screen display parameters under various environmental conditions, improving user experience and simplifying operation procedures is achieved.

[0012] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0013] For example, please refer to the attached Figure 1 , this application provides a mobile phone screen display optimization method combined with scene monitoring, which specifically includes the following steps: Step 1: Call the sensor array of the target mobile phone to perform scene monitoring in a preset monitoring window to obtain a scene monitoring data set sequence.

[0014] Specifically, the target mobile phone is a mobile phone for which screen display optimization is to be performed. The sensor array in the target mobile phone is called, and the sensor array includes multiple different types of sensors, such as accelerometers, gyroscopes, temperature sensors, light sensors, etc., for obtaining different types of data. The sensor array is set in a preset monitoring window, and the preset monitoring window refers to selecting a monitored area or range within a preset time and space range to obtain a scene monitoring data set sequence. Among them, the preset monitoring window is customized by a person skilled in the art according to actual conditions. For example, when monitoring the motion state of the target mobile phone, the monitoring window includes the acceleration and rotation state of the mobile phone; when monitoring the environmental conditions of the target mobile phone, the monitoring window includes light, temperature, etc. By obtaining the scene monitoring data set, the data set sequence is formed in chronological order as the scene monitoring data set sequence. For example, the temperature sensor of the mobile phone records data once every second, and then forms a time series to show the temperature change of the mobile phone within a certain period of time for subsequent analysis or processing.

[0015] Step 2: performing interactive correlation analysis of adjacent data in sequence according to the sequence of scene monitoring data sets in the scene monitoring data set sequence to determine interactively correlated scene monitoring data sets.

[0016] Specifically, according to the order of data sets in the scene monitoring data set sequence, adjacent data interactive correlation analysis is performed on two adjacent data sets in turn. Adjacent data interactive correlation analysis refers to comparing each pair of adjacent data sets to analyze the similarities and change trends between the two. Through adjacent data interactive correlation analysis, the correlation between the two data sets is calculated. Then, the same analysis is performed on the remaining data, and so on, until all data sets are processed, and then the interactively correlated scene monitoring data set is obtained, and the mutual correlation and change rules between all adjacent data sets are obtained, so as to obtain the dynamic change process of the data.

[0017] Step 3: Using the data type as an index, perform a centralized analysis of the scene monitoring data set sequence for data of the same type, and determine a median value set of the scene monitoring data set.

[0018] Specifically, using data type as an index means that when analyzing the scene monitoring data set, it is classified according to different data types (such as temperature, humidity, pressure, etc.) to ensure that the monitoring results of each data type are processed and analyzed separately. Next, the centralized analysis of the same type of data on the scene monitoring data set sequence means that the monitoring data with the same data type are analyzed together. For example, all data about temperature will be divided into one group, and all data about humidity will be divided into another group, so as to understand the changing trends and laws of each data type, so as to make more accurate decisions. Then, determining the median set of scene monitoring data means calculating a representative data value in each data set of the same type, and obtaining a numerical value representing the typical level of the data set by calculating the central tendency, such as the mean, mode or median.

[0019] Step 4: taking the median set of the scene monitoring data as foreground data, taking the interactively associated scene monitoring data set as background data, performing screen display parameter optimization screening in the display optimization space, and determining target screen display optimization parameters.

[0020] Specifically, through sensors or other monitoring devices, the median set of scene monitoring data is used as foreground data, which means extracting representative numerical data from the actual scene monitoring, reflecting certain characteristics of the scene, such as temperature, humidity, light intensity, etc. Then, the interactively correlated scene monitoring data is collected as background data, representing other information related to the foreground data, such as ambient conditions or historical data. After taking the foreground data and background data as input, optimization screening is performed in the display optimization space, that is, the parameters of the display effect are adjusted according to these data to ensure that the final display can best adapt to the current environment and needs. By screening in the display optimization space, a suitable display brightness and contrast can be calculated to ensure that the display can present the content clearly and comfortably under the current temperature and humidity conditions. Finally, through the screening process, the target screen display optimization parameters are determined to help achieve the best display effect under specific environmental conditions.

[0021] Step 5: Optimizing the display of the screen of the target mobile phone based on the target screen display optimization parameters.

[0022] Specifically, the screen of the target mobile phone is adjusted according to the target screen display optimization parameters. The target screen display optimization parameters are a set of display settings adapted to the current environmental conditions obtained by analyzing the foreground data and background data, including factors such as brightness, contrast, and color temperature, which will affect the display effect of the mobile phone screen, such as making the screen clearer or energy-saving in different lighting environments. For example, when the indoor temperature is 20 degrees Celsius and the humidity is 50%, the optimization parameters obtained are that the screen brightness is set to 200 and the color temperature is set to 6000 Kelvin, which can maintain good visibility in both daytime and low-light environments and reduce eye fatigue. Then, based on the optimization parameters, the screen of the target mobile phone will be adjusted according to the preset values, and finally the display effect will be optimized to adapt to the current usage scenarios and environmental conditions, thereby providing a more comfortable visual experience.

[0023] The mobile phone screen display optimization method combined with scene monitoring can achieve the technical goal of dynamic display optimization adjustment based on real-time environmental data and device characteristics, and achieve the technical effect of intelligently and automatically adjusting screen display parameters under various environmental conditions, improving user experience and simplifying operation processes.

[0024] Furthermore, the present application also includes: Extract the first scene monitoring data set at the first position and the second scene monitoring data set at the second position in the scene monitoring data set sequence; perform adjacent data interactive correlation analysis on the first scene monitoring data set and the second scene monitoring data set to determine a first adjacent associated scene monitoring data set; extract the third scene monitoring data set at the third position in the scene monitoring data set sequence, perform adjacent data interactive correlation analysis on it and the first adjacent associated scene monitoring data set to determine a second adjacent associated scene monitoring data set; perform adjacent data interactive correlation analysis in sequence until reaching the end of the scene monitoring data set, and use the adjacent associated scene monitoring data set obtained from the last analysis as the interactively associated scene monitoring data set.

[0025] Specifically, from the scene monitoring data set sequence, the first scene monitoring data set at the first position and the second scene monitoring data set at the second position are extracted to compare and analyze the environment or device status at different times. For example, the first scene monitoring data set contains the status data of the mobile phone when it starts to move, while the second scene monitoring data set contains the status data of the mobile phone after a few seconds of movement.

[0026] Next, the first scene monitoring data set and the second scene monitoring data set are subjected to adjacent data interactive correlation analysis to find out the relationship and dependency between the two sets of data sets. Adjacent data interactive correlation analysis refers to comparing two adjacent data sets and analyzing the changing trends and patterns between the two. For example, assuming that the first scene monitoring data set shows that the acceleration of the mobile phone gradually increases, while the second scene monitoring data set shows that the acceleration continues to increase, the interactive correlation analysis can be used to determine whether the trend of acceleration growth is coherent, thereby inferring whether the mobile phone continues to accelerate, and then obtaining the first adjacent correlation scene monitoring data set, which represents the correlation characteristics between the two data sets.

[0027] Subsequently, the third scene monitoring data set located in the third position is extracted, and adjacent data interactive correlation analysis is performed on it and the first adjacent associated scene monitoring data set, and then the third data set is further compared and correlated with the previous correlation result to analyze the relationship between the third data set and the first two data sets, and the second adjacent associated scene monitoring data set is obtained, which represents the correlation result between the third data set and the first two data sets.

[0028] Next, the adjacent data interactive correlation analysis is performed on the remaining scene monitoring data sets in turn until the end of the scene monitoring data set is reached. Each time the correlation analysis is performed, a new adjacent correlation scene monitoring data set is obtained as the interactive correlation scene monitoring data set, which represents the correlation characteristics between the current data set and all previous data sets, helping to obtain the law of data changes over time or events.

[0029] By performing adjacent data interactive correlation analysis on each data set in the scene monitoring data set sequence, the relationship between data at different times or states is gradually extracted, and finally a comprehensive interactive correlation data set is obtained, which can obtain the changing trend of the data and provide strong support for further decision-making and optimization.

[0030] Furthermore, the present application also includes: A mapping association analyzer is used to perform mapping calculation on the first scene monitoring data set and the second scene monitoring data set to determine a first adjacency association similarity set; the first adjacency association similarity set is normalized, and the processing result is embedded in a matrix to obtain a first adjacency association matrix; an association operation analyzer is called to perform convolution analysis on the first adjacency association matrix and the first adjacency association similarity set to obtain a first adjacency association scene monitoring data set.

[0031] Specifically, a mapping association analyzer is used to perform mapping calculations on the first scene monitoring data set and the second scene monitoring data set. Mapping calculation refers to mapping the data in the two data sets through a mathematical or algorithmic model so that they can be compared and analyzed in the same dimension or space. For example, assuming that the first scene monitoring data set records the acceleration of the mobile phone, and the second scene monitoring data set records the speed of the mobile phone, through mapping calculations, different types of data are converted to the same format or dimension for subsequent association analysis. The first adjacent association similarity set is determined by mapping calculations, indicating the similarity or mutual relationship between the two data sets. The higher the similarity, the higher the similarity of the two data sets, and the lower the similarity, the greater the difference between the two.

[0032] Next, the first adjacency association similarity set is normalized, and the processing result is embedded in the matrix to obtain the first adjacency association matrix. Normalization is to convert data of different scales into a unified range, such as converting the value from the original range to between [0, 1]. Taking softmax calculation as an example, the similarity value is converted into a probability value, so that the sum of all similarity values ​​is 1, and then all values ​​of the first adjacency association similarity set are unified for subsequent analysis.

[0033] Subsequently, the association operation analyzer is called to perform convolution analysis on the first adjacency association matrix and the first adjacency association similarity set. The association operation analyzer includes a mathematical operation architecture of a convolutional neural network, which can perform weighted processing on the data in the first adjacency association matrix and extract the main features in the first adjacency association similarity set. For example, by focusing on the higher similarity part in the first adjacency association similarity set through convolution operation, a deeper association law between the data is excavated, and then the first adjacency association scene monitoring data set is obtained, which includes the convolution analysis results between the first adjacency association matrix and the first adjacency association similarity set, and reveals the relationship between more detailed scene monitoring data.

[0034] Mapping calculations are performed through the mapping association analyzer to quantify the similarities between different scenario data sets, and they are converted into a unified format through normalization. Then, convolution analysis is used to extract deeper correlation features between data sets, and valuable information is mined from multiple data sets to provide support for subsequent data analysis and decision-making.

[0035] Furthermore, the present application also includes: Construct a mapping association analyzer, wherein the mapping association analyzer includes a mapping association formula, and the mapping association formula is: is the i-th adjacent association similarity obtained after mapping association analysis of the i-th scene monitoring data in the first scene monitoring data set and the second scene monitoring data set, is the jth data feature of the i-th scene monitoring data in the first scene monitoring data set, is the jth data feature of the scene monitoring data in the second scene monitoring data set, The weight of the j-th data feature in the i-th scene monitoring data when performing mapping association analysis, is the total number of data features contained in the i-th scene monitoring data, is an integer greater than or equal to 1.

[0036] Specifically, a mapping association analyzer is constructed, and then the relationship between different scene monitoring data sets is quantitatively analyzed through mathematical models. The mapping association analyzer contains a mapping association formula, which can calculate according to the characteristics of the scene monitoring data to obtain the correlation between the data, and convert the relationship between two different scene data sets into numerical results through calculation, so as to compare and analyze the similarities or differences of these data sets.

[0037] In the mapping association formula, the i-th adjacent association similarity is obtained by performing mapping association analysis on the i-th scene monitoring data in the first scene monitoring data set and the second scene monitoring data set, which is recorded as The similarity value reflects the degree of association between the corresponding data in the two data sets. The larger the value of the i-th adjacent association similarity, the stronger the association between the two, and vice versa. Next, the j-th data feature of the i-th scene monitoring data in the first scene monitoring data set The weight of the jth data feature of the i-th scene monitoring data in the second scene monitoring data set They represent the specific attributes or indicators of each data point in the data set, such as the acceleration, angular velocity, temperature, etc. of the target mobile phone. When performing mapping association analysis, we should not only focus on a single data point, but also consider multiple features of each data point and calculate the similarity based on multiple features.

[0038] In addition, the weight of the jth data feature of the i-th scene monitoring data in the mapping association analysis is It refers to the degree of influence on the final result when performing mapping association analysis. The features with larger weights will have a greater effect in the calculation, and vice versa. Finally, the total number of data features contained in the i-th scene monitoring data Represents the total number of features that need to be considered in each data set. These features may include acceleration, temperature, pressure, etc., and each feature may have a different degree of impact on the final result.

[0039] Integer greater than or equal to 1 The number of data features in a data set can be any integer, at least 1, indicating that each data set contains at least one data feature for analysis.

[0040] By building a mapping association analyzer and defining a mapping association formula, mathematical methods are used to quantitatively analyze the data features in different scene monitoring data sets, calculate the similarity, and thus identify the association between different data sets, thereby identifying and adjusting the cutting process or other control parameters to improve accuracy and efficiency.

[0041] Furthermore, the present application also includes: Acquire multiple sample adjacency association matrices and multiple sample adjacency association similarity sets, and corresponding multiple sample adjacency association scene monitoring data sets as training data sets; divide the training data sets into training sets and verification sets according to a preset ratio; use the training sets to train a framework built based on a convolutional network, and use the verification sets to supervise the training results during training until the training converges, thereby obtaining the trained association operation analyzer.

[0042] Specifically, multiple sample adjacency association matrices and multiple sample adjacency association similarity sets, as well as corresponding multiple sample adjacency association scene monitoring data sets are obtained as training data sets, which means extracting historical data corresponding to the adjacency association matrix, the adjacency association similarity set, and the adjacency association scene monitoring data set from historical data. The adjacency association matrix contains the degree of association between sample data, the adjacency association similarity set indicates the degree of similarity between each data set and other data sets, and the adjacency association scene monitoring data set contains specific monitoring data. The training data set is used as the basis for training the model through supervised learning.

[0043] Next, the training data set is divided into a training set and a validation set according to the preset ratio. The training set is the sample data used to train the model, while the validation set is used to evaluate the performance and accuracy of the model during the training process. For example, the training set is divided into 70% and the validation set is divided into 30%. This division ensures that the model can not only learn the characteristics of the data during training, but also evaluate the generalization ability of the model through the validation set to avoid overfitting.

[0044] Then, the training set is used to train the framework built based on the convolutional network, and the validation set is used to supervise the training results during training until the training converges to obtain a trained association operation analyzer. The convolutional network is a deep learning model that automatically extracts features from the data through the convolution layer and learns and optimizes through a multi-layer network. During the training process, the training set data is used to adjust the model parameters, and the accuracy of the model is continuously checked through the validation set. When the model error is minimized and no longer significantly improved, the training process is completed, and the model converges to finally obtain a trained association operation analyzer that can perform accurate association calculations based on new input data.

[0045] By obtaining multiple sample data and dividing them into training sets and validation sets, a convolutional network-based model is trained. By learning the features in the training data and continuously adjusting and optimizing on the validation set, an association operation analyzer that can accurately perform data association analysis is finally obtained, thereby effectively improving the accuracy of data analysis and prediction, thereby supporting more efficient decision-making and optimization processes.

[0046] Furthermore, the present application also includes: Using the data type as an index, perform the same type of cross-time series aggregation on the scene monitoring data set sequence to obtain multiple aggregated scene monitoring data sets, each aggregated scene monitoring data set is all monitoring data of a data type within the preset monitoring window; extract a first aggregated scene monitoring data set from the multiple aggregated scene monitoring data sets, perform data set median calculation on the first aggregated scene monitoring data set to obtain the first scene monitoring data set median; traverse the multiple aggregated scene monitoring data sets to perform data set median calculation to obtain the scene monitoring data set median set.

[0047] Specifically, the monitoring data is classified according to the data type (such as acceleration, temperature, humidity, etc.), and then the data of the same type is aggregated within a preset time window, and the data of the same type is merged in the time dimension to analyze the overall trend and change pattern of the data. For example, if there are three different data types, each type of data is recorded at different time points, after cross-time series aggregation, all the data of each data type in the preset time window is obtained, and then the change of each type of data over time is obtained.

[0048] Next, a first aggregated scene monitoring data set is randomly selected from multiple aggregated data sets, and then the central value of the data in the set is calculated. The central value usually refers to the median or mean, which is used to represent the typical value of the data set. The central value can help us better understand the distribution of the data. For example, if the first aggregated data set contains acceleration data at different time points, then the central value is the average value of the acceleration data, representing the overall level of acceleration in this time window.

[0049] Then, the same central value calculation is performed on all aggregated scene monitoring data sets. By accessing all data sets in turn, a set containing the central value of each aggregated scene data set is obtained as the basis for analyzing data characteristics, thereby obtaining the overall trend of the data and the relationship between various types of data.

[0050] By aggregating scene monitoring data across time series with data types as indexes, data of the same type can be merged and each data set can be summarized through central value calculation. This not only allows us to clearly see the changing trends of different types of data within the time window, but also reveals the overall characteristics of the data through the aggregated central value, which in turn helps with further analysis and decision-making.

[0051] Furthermore, the present application also includes: The first aggregated scene monitoring data set is cleaned for edge values ​​using a box plot method to obtain a first cleaned aggregated scene monitoring data set; the mean of the first cleaned aggregated scene monitoring data set is calculated to obtain a median value of the first scene monitoring data set.

[0052] Specifically, the box plot method is a method for identifying outliers (i.e., edge values) in data. By drawing a box plot of the data, calculating the quartiles of the data, and identifying data points that are beyond the upper and lower quartiles, these data points are considered outliers or extreme values. The box plot method is used to clean up irregular outliers, making the data more concentrated and stable. When the box plot method is applied to the first aggregation scenario monitoring data set, it helps identify and remove abnormal data that is too high or too low, thereby obtaining a more accurate and regular data set. For example, if there are extreme values ​​in the original data (such as the temperature recorded by the temperature sensor is 50 degrees Celsius, but the actual temperature is only 20 degrees Celsius), the extreme values ​​will be identified and cleared by the box plot method.

[0053] Next, after removing the outliers, the mean of the cleaned data set is calculated. The mean is the average value of all values ​​in the data set and is used to represent the typical level of the data. The calculation of the mean helps to obtain the overall trend and characteristics of the cleaned data set. For example, if the cleaned temperature data set includes temperature values ​​at multiple time points, then by calculating the mean of the temperature values, a value representing the temperature level of the time period can be obtained, thereby effectively describing the monitoring data of the scene.

[0054] By using the box plot method to clean outliers in the data, we can effectively remove marginal data and improve the accuracy and representativeness of the data. Then, by calculating the mean of the cleaned data set, we can get a value that can represent the typical level of the data set, which helps to remove noise and ensure the quality of the data, thus providing a more accurate basis for subsequent data analysis.

[0055] Furthermore, the present application also includes: Acquire the display optimization space, wherein the display optimization space is a two-dimensional space, the horizontal axis is foreground data, the vertical axis is background data, the display optimization space includes multiple spatial points, and each spatial point includes a screen display optimization parameter; input the median set of the scene monitoring data and the interactively associated scene monitoring data set into the display optimization space to obtain a target point; add the spatial points from the multiple spatial points whose distance to the target point is within a preset distance threshold into a set of adjacent spatial points; calculate the mean of the multiple screen display optimization parameters corresponding to the set of adjacent spatial points to obtain the target screen display optimization parameter.

[0056] Specifically, obtaining the display optimization space refers to a two-dimensional space set when constructing a spatial model for optimizing the display effect. Each spatial point contains a screen display optimization parameter to indicate how to adjust the display effect according to different combinations of foreground and background data. Among them, the horizontal axis represents the foreground data, and the vertical axis represents the background data. For example, the foreground data is the color brightness of the image, and the background data is the ambient light intensity. Each point in the space represents a specific display setting.

[0057] Next, inputting the scene monitoring data set median and the interactively correlated scene monitoring data set into the display optimization space means bringing the actual collected data (such as sensor measurements, environmental data, etc.) into the preset optimization space model to obtain the target point. The target point is determined by the combination of foreground and background data, and represents the best display state to be achieved under the existing conditions. For example, if the foreground data is the indoor temperature and the background data is the external weather conditions, the target point will combine these two sets of data to find the most suitable display settings.

[0058] Then, by adding multiple spatial points whose distances to the target point are within the preset distance threshold to the set of neighboring spatial points, find spatial points that are very close to the target point. Neighboring spatial points represent other display settings similar to the current display requirements and may provide important references for optimization. For example, if the target point is a display setting at 30 degrees Celsius and 50% humidity, then the neighboring spatial points may be settings at 28 degrees Celsius and 55% humidity.

[0059] Finally, calculating the mean of multiple screen display optimization parameters corresponding to the set of neighboring spatial points means calculating the average value based on the display parameters of the neighboring points, thereby obtaining a new optimization parameter that can be used to adjust the actual display effect to achieve the best visual experience. For example, if the brightness and contrast values ​​of the neighboring spatial points are 20, 30, 35 for brightness and 10, 12, 13 for contrast, then the calculated mean will provide a comprehensive parameter value indicating the adjustment of the screen settings.

[0060] By introducing the monitored data into the preset display optimization space, calculating and analyzing the display optimization parameters of similar data points, we can eventually come up with a display setting that best suits the current environment and needs. By gradually screening adjacent optimization parameters, we can ensure that the final display effect can reach the optimal level under the preset conditions, thereby improving the user's visual experience and the accuracy of the display effect.

[0061] In summary, the mobile phone screen display optimization method combined with scene monitoring provided by this application has the following technical effects: The sensor array of the target mobile phone is called to perform scene monitoring in a preset monitoring window to obtain a scene monitoring data set sequence; the adjacent data interactive correlation analysis is performed in sequence according to the sequence of scene monitoring data sets in the scene monitoring data set sequence to determine the interactively correlated scene monitoring data set; the scene monitoring data set sequence is subjected to a centralized analysis of data of the same type with the data type as an index to determine the median set of the scene monitoring data; the scene monitoring data set median set is used as foreground data, and the interactively correlated scene monitoring data set is used as background data to perform screen display parameter optimization screening in a display optimization space to determine the target screen display optimization parameters; the screen of the target mobile phone is displayed optimized based on the target screen display optimization parameters, that is, by realizing the technical goal of dynamic display optimization adjustment based on real-time environmental data and device characteristics, the technical effect of intelligently and automatically adjusting the screen display parameters under various environmental conditions, improving the user experience and simplifying the operation process is achieved.

[0062] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0063] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A mobile phone screen display optimization method combined with scene monitoring, characterized in that: The method comprises: Invoke the sensor array of the target mobile phone to perform scene monitoring in a preset monitoring window to obtain a scene monitoring data set sequence; According to the sequence of scene monitoring data sets in the scene monitoring data set sequence, adjacent data interactive correlation analysis is performed in sequence to determine interactively correlated scene monitoring data sets; Using the data type as an index, performing a centralized analysis of the scene monitoring data set sequence on data of the same type, and determining a median value set of the scene monitoring data set; Taking the median set of the scene monitoring data as foreground data and taking the interactively associated scene monitoring data as background data, performing screen display parameter optimization screening in the display optimization space to determine the target screen display optimization parameters; The screen of the target mobile phone is displayed optimized based on the target screen display optimization parameters.

2. The method for optimizing mobile phone screen display in combination with scene monitoring according to claim 1, characterized in that: According to the sequence of scene monitoring data sets in the scene monitoring data set sequence, adjacent data interactive correlation analysis is performed in sequence to determine interactively correlated scene monitoring data sets, including: Extracting a first scene monitoring data set located at the first position and a second scene monitoring data set located at the second position in the scene monitoring data set sequence; Performing adjacent data interactive correlation analysis on the first scene monitoring data set and the second scene monitoring data set to determine a first adjacent correlated scene monitoring data set; Extracting a third scene monitoring data set located at the third position in the scene monitoring data set sequence, performing adjacent data interactive correlation analysis on the third scene monitoring data set and the first adjacent associated scene monitoring data set to determine a second adjacent associated scene monitoring data set; The adjacent data interactive correlation analysis is performed in sequence until the end of the scene monitoring data set is reached, and the adjacent correlation scene monitoring data set obtained from the last analysis is collected as the interactive correlation scene monitoring data set.

3. The method for optimizing mobile phone screen display in combination with scene monitoring as claimed in claim 2, characterized in that: Performing adjacent data interactive correlation analysis on the first scene monitoring data set and the second scene monitoring data set to determine a first adjacent correlated scene monitoring data set includes: Using a mapping association analyzer to perform mapping calculation on the first scene monitoring data set and the second scene monitoring data set to determine a first adjacency association similarity set; Normalizing the first adjacency association similarity set, and embedding the processing result into a matrix to obtain a first adjacency association matrix; An association operation analyzer is called to perform convolution analysis on the first adjacency association matrix and the first adjacency association similarity set to obtain a first adjacency association scene monitoring data set.

4. The method for optimizing mobile phone screen display in combination with scene monitoring as claimed in claim 3, characterized in that: include: Construct a mapping association analyzer, wherein the mapping association analyzer includes a mapping association formula, and the mapping association formula is: ； in, is the i-th adjacent association similarity obtained after mapping association analysis of the i-th scene monitoring data in the first scene monitoring data set and the second scene monitoring data set, is the jth data feature of the i-th scene monitoring data in the first scene monitoring data set, is the jth data feature of the scene monitoring data in the second scene monitoring data set, The weight of the j-th data feature in the i-th scene monitoring data when performing mapping association analysis, is the total number of data features contained in the i-th scene monitoring data, is an integer greater than or equal to 1.

5. The method for optimizing mobile phone screen display in combination with scene monitoring as claimed in claim 3, characterized in that: include: Obtain multiple sample adjacency association matrices and multiple sample adjacency association similarity sets, as well as corresponding multiple sample adjacency association scene monitoring data sets as training data sets; Dividing the training data set into a training set and a validation set according to a preset ratio; The training set is used to train the framework built based on the convolutional network, and the verification set is used to supervise the training results during the training until the training converges, thereby obtaining the trained association operation analyzer.

6. The method for optimizing mobile phone screen display in combination with scene monitoring according to claim 1, characterized in that: Using the data type as an index, the scene monitoring data set sequence is subjected to a centralized analysis of data of the same type to determine a set of median values ​​of the scene monitoring data set, including: Using the data type as an index, perform cross-time series aggregation of the scene monitoring data set sequence of the same type to obtain multiple aggregated scene monitoring data sets, each aggregated scene monitoring data set being all monitoring data of a data type within the preset monitoring window; Extracting a first aggregated scene monitoring data set from the multiple aggregated scene monitoring data sets, performing data median calculation on the first aggregated scene monitoring data set, and obtaining a first scene monitoring data median; The plurality of aggregated scene monitoring data sets are traversed to perform data median calculation to obtain the scene monitoring data set median set.

7. The method for optimizing mobile phone screen display in combination with scene monitoring as claimed in claim 6, characterized in that: include: Using a box plot method to clean the edge values ​​of the first aggregated scene monitoring data set to obtain a first cleaned aggregated scene monitoring data set; Calculate the mean of the first cleaning aggregation scene monitoring data set to obtain the median of the first scene monitoring data set.

8. The method for optimizing mobile phone screen display in combination with scene monitoring according to claim 1, characterized in that: The median set of the scene monitoring data is used as foreground data, the interactive correlation scene monitoring data set is used as background data, and screen display parameter optimization screening is performed in the display optimization space to determine the target screen display optimization parameters, including: Acquire the display optimization space, wherein the display optimization space is a two-dimensional space, the abscissa axis is foreground data, the ordinate axis is background data, the display optimization space includes a plurality of space points, and each space point includes a screen display optimization parameter; Inputting the scene monitoring data set median value set and the interactively associated scene monitoring data set into the display optimization space to obtain a target point; Adding the spatial points whose distances to the target point are within a preset distance threshold from the multiple spatial points into a set of adjacent spatial points; The average values ​​of a plurality of screen display optimization parameters corresponding to the set of adjacent spatial points are calculated to obtain the target screen display optimization parameters.

Images