CN117711295A

CN117711295A - Display module control method, device, chip and medium based on artificial intelligence

Info

Publication number: CN117711295A
Application number: CN202410167573.7A
Authority: CN
Inventors: 汪金球; 肖琼
Original assignee: SHENZHEN DONGLU TECHNOLOGY CO LTD
Current assignee: SHENZHEN DONGLU TECHNOLOGY CO LTD
Priority date: 2024-02-06
Filing date: 2024-02-06
Publication date: 2024-03-15

Abstract

The application relates to the technical field of artificial intelligence and discloses a display module control method, device, chip and medium based on artificial intelligence. The method comprises the following steps: acquiring a plurality of display modules of a target display screen, testing to obtain a response behavior data set, and performing module arrangement analysis to obtain module arrangement positions; performing module display cooperative relation analysis to obtain module display cooperative relation and dynamic characteristic analysis to obtain dynamic characteristic data; extracting features to obtain a dynamic feature set and external optical influence feature components; generating a first display parameter combination, combining the acquired state feedback data, and analyzing a parameter compensation strategy to obtain the parameter compensation strategy; and carrying out parameter optimization solution to generate a second display parameter combination, and carrying out display control on the target display screen through the second display parameter combination corresponding to each display module by adopting a subdivision rectangular global optimization algorithm.

Description

Display module control method, device, chip and medium based on artificial intelligence

Technical Field

The application relates to the technical field of artificial intelligence, in particular to a display module control method, device, chip and medium based on artificial intelligence.

Background

In the current development background of display technology, a display module is taken as a basic component for displaying images and videos, and plays a vital role in providing high-quality visual experience. With the rapid development of technology, especially in the fields of intelligent devices and entertainment media, the requirements of people on display quality are increasing. This involves not only the sharpness and color accuracy of the image, but also the ability to quickly respond to dynamic scenes and adapt to the display effects under different ambient light conditions. However, the conventional display module control method generally adopts a fixed algorithm, lacks dynamic adjustment capability, and is difficult to meet the requirements of various environments and high-standard personalized display.

In addition, existing display technologies face challenges in handling multiple display modules to work in concert. Because of the difference between the performance characteristics and the response behaviors of each display module, how to precisely control each module to realize the consistency and optimization of the overall display is a technical difficulty. Meanwhile, external environmental factors, especially the change of optical parameters, have remarkable influence on the display effect, but the traditional method often neglects the influence, so that the stability and adaptability of the display effect in different environments are insufficient.

Disclosure of Invention

The application provides a display module control method, device, chip and medium based on artificial intelligence, which are used for improving the accuracy of display module control.

In a first aspect, the present application provides an artificial intelligence based display module control method, including:

acquiring a plurality of display modules of a target display screen, performing dynamic response test on the plurality of display modules based on a Newmark-beta algorithm to obtain a response behavior data set of each display module, and performing module arrangement analysis on the plurality of display modules to obtain a module arrangement position corresponding to each display module;

performing module display cooperative relation analysis on the plurality of display modules based on the response behavior data set and the module arrangement positions to obtain module display cooperative relation, and performing dynamic characteristic analysis on the plurality of display modules according to the module display cooperative relation to obtain dynamic characteristic data of each display module;

performing feature extraction and feature classification on the dynamic characteristic data of each display module to obtain a dynamic feature set of each display module, and performing external optical parameter monitoring and feature extraction on the plurality of display modules to obtain external optical influence feature components of each display module;

Performing display parameter analysis on the plurality of display modules according to the dynamic feature set and the external optical influence feature components through a multi-agent reinforcement learning algorithm to generate a first display parameter combination corresponding to each display module;

performing display control on the plurality of display modules according to the first display parameter combination, collecting state feedback data corresponding to each display module, and performing parameter compensation strategy analysis on each display module based on the state feedback data corresponding to each display module to obtain a parameter compensation strategy corresponding to each display module;

and carrying out parameter optimization solving on the first display parameter combination based on the parameter compensation strategy, generating a second display parameter combination corresponding to each display module, and carrying out display control on the target display screen through the second display parameter combination corresponding to each display module by adopting a subdivision rectangular global optimization algorithm.

In a second aspect, the present application provides an artificial intelligence based display module control device, the artificial intelligence based display module control device includes:

the acquisition module is used for acquiring a plurality of display modules of the target display screen, carrying out dynamic response test on the plurality of display modules based on a Newmark-beta algorithm to obtain a response behavior data set of each display module, and carrying out module arrangement analysis on the plurality of display modules to obtain a module arrangement position corresponding to each display module;

The analysis module is used for carrying out module display cooperative relation analysis on the plurality of display modules based on the response behavior data set and the module arrangement position to obtain a module display cooperative relation, and carrying out dynamic characteristic analysis on the plurality of display modules according to the module display cooperative relation to obtain dynamic characteristic data of each display module;

the feature extraction module is used for carrying out feature extraction and feature classification on the dynamic characteristic data of each display module to obtain a dynamic feature set of each display module, and carrying out external optical parameter monitoring and feature extraction on the plurality of display modules to obtain external optical influence feature components of each display module;

the processing module is used for carrying out display parameter analysis on the plurality of display modules according to the dynamic characteristic set and the external optical influence characteristic components through a multi-agent reinforcement learning algorithm to generate a first display parameter combination corresponding to each display module;

the feedback module is used for performing display control on the plurality of display modules according to the first display parameter combination, collecting state feedback data corresponding to each display module, and performing parameter compensation strategy analysis on each display module based on the state feedback data corresponding to each display module to obtain a parameter compensation strategy corresponding to each display module;

And the solving module is used for carrying out parameter optimization solving on the first display parameter combination based on the parameter compensation strategy, generating a second display parameter combination corresponding to each display module, and carrying out display control on the target display screen through the second display parameter combination corresponding to each display module by adopting a subdivision rectangular global optimization algorithm.

The third aspect of the present application provides a chip, where the chip is configured to perform the artificial intelligence-based display module control method described above.

A fourth aspect of the present application provides a computer readable storage medium having instructions stored therein, which when run on a computer, cause the computer to perform the artificial intelligence based display module control method described above.

According to the technical scheme, dynamic response test and accurate analysis of the arrangement positions of the modules are carried out through the Newmark-beta algorithm, so that the optimal display effect of each display module at a specific position can be ensured. And the module display cooperative relation analysis and dynamic characteristic data analysis are combined, so that the whole display system can realize high synchronization among all modules, and the overall display quality is improved. The display parameters are analyzed by utilizing the multi-agent reinforcement learning algorithm, and the display parameters can be adjusted in real time based on environmental changes and module states, so that self-adaptive adjustment is realized. The collection of state feedback data and the analysis of parameter compensation strategies further enhance the adaptability of the system to external changes and the stability of display effects. The dynamic characteristics and external influences of each display module are accurately mastered through feature extraction and feature classification, so that resources can be utilized more effectively, and resource waste is avoided. And the display parameters are subjected to global optimization by adopting a subdivision rectangular global optimization algorithm, so that the efficient configuration and use of resources are realized on the premise of meeting the display requirements. The collected state feedback data and parameter compensation strategies not only can adjust the current state, but also can prevent potential display problems, and the stability and reliability of the system are enhanced. The stability of the system in long-term operation is further ensured by the aid of parameter optimization solving and the use of a global optimization algorithm, and maintenance cost and frequency are reduced. Through fine display module assembly control, can provide richer, clear and vivid visual effect, and then improved the rate of accuracy of display module assembly control.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained based on these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram of an embodiment of a display module control method based on artificial intelligence in an embodiment of the application;

fig. 2 is a schematic diagram of an embodiment of an artificial intelligence-based display module control device in an embodiment of the present application.

Detailed Description

The embodiment of the application provides a display module control method, device, chip and medium based on artificial intelligence. The terms "first," "second," "third," "fourth" and the like in the description and in the claims of this application and in the above-described figures, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

For ease of understanding, the following describes a specific flow of an embodiment of the present application, referring to fig. 1, and one embodiment of a display module control method based on artificial intelligence in the embodiment of the present application includes:

step S101, acquiring a plurality of display modules of a target display screen, performing dynamic response test on the plurality of display modules based on a Newmark-beta algorithm to obtain a response behavior data set of each display module, and performing module arrangement analysis on the plurality of display modules to obtain module arrangement positions corresponding to each display module;

it can be understood that the execution subject of the present application may be an artificial intelligence based display module control device, and may also be a terminal or a server, which is not limited herein. The embodiment of the present application will be described by taking a server as an execution body.

Specifically, a plurality of display modules of a target display screen are obtained, and dynamic response test is carried out on the display modules based on a Newmark-beta algorithm. The Newmark-beta algorithm is a dynamic numerical analysis method and is widely applied to the field of structural engineering, in particular to dynamic response analysis. The algorithm can calculate the behavior of the display module under different excitation by means of numerical integration, so that an initial behavior data set of each display module is obtained. And cleaning the initial behavior data set of each display module, so as to improve the data quality and the analysis accuracy. Data cleansing typically involves operations to remove extraneous data, correct erroneous data, etc., to ensure the validity of subsequent analysis. And after cleaning, obtaining a first behavior data set of each display module. And performing outlier detection and removal on the first behavior data set of each display module. Outliers, or outliers, refer to those values that do not conform to a general data pattern, and are caused by various factors, such as measurement errors or abnormal environmental conditions. Removing outliers helps to ensure consistency and reliability of the data set. And after the processing, obtaining a second behavior data set of each display module. And (5) performing scale standardization treatment. And the scale inconsistency existing between different data sets is eliminated, so that the data is more comparable. Scale normalization generally involves adjusting the range and distribution of data to conform to a standard or distribution pattern, resulting in a set of response behavior data. And carrying out display module coding on the plurality of display modules, and carrying out module arrangement analysis according to the coding values. Coding is a method of converting data into a format that is easy to process and can help identify and distinguish between different display modules. Based on the coding values, effective arrangement analysis is carried out on the display modules, and finally the optimal arrangement position of each display module is determined.

Step S102, performing module display cooperative relation analysis on a plurality of display modules based on a response behavior data set and module arrangement positions to obtain module display cooperative relation, and performing dynamic characteristic analysis on the plurality of display modules according to the module display cooperative relation to obtain dynamic characteristic data of each display module;

specifically, dynamic characteristic analysis is performed on the multiple display modules, including frequency response calculation, stability calculation and sensitivity calculation, so as to obtain the relevant index of each display module. The frequency response calculation is to analyze the response capability of the display module under the stimulation of different frequencies, and obtain the frequency response index of each display module through calculation, wherein the indexes reveal the response speed and degree of the module to the change of the input signal. And (3) performing stability calculation, and evaluating the performance maintaining capability of the display module under long-time operation or different environmental conditions. The stability index may help to understand the reliability and failure rate of the module in various situations, which helps to ensure long-term operation of the display system and reduce maintenance costs. Stability indexes of each display module are obtained through stability calculation, and the stability indexes are helpful for predicting and preventing potential performance degradation. And performing sensitivity calculation on each display module. The sensitivity index reflects the degree of response of the module to changes in external variables, such as sensitivity to temperature, light, or other environmental factors. And carrying out cooperative relation analysis on the frequency response index, the stability index and the sensitivity index according to the arrangement positions of the modules, so as to understand the interaction among different modules and how the interaction affects the overall display effect. The module display synergistic relationship analysis can reveal not only the characteristics of individual modules, but also how they work together to produce the best overall performance. And according to the obtained module display cooperative relationship, carrying out dynamic characteristic analysis on each display module. All the previous analyses are integrated to get a full understanding of how each display module behaves in practical applications. This includes how the modules respond to various inputs, their performance under different operating conditions, and how they cooperate with other modules to achieve optimal performance of the overall display. Through the comprehensive dynamic characteristic analysis, each module is ensured to be in the optimal working state, so that the performance and the efficiency of the whole display system are greatly improved.

Step S103, carrying out feature extraction and feature classification on the dynamic characteristic data of each display module to obtain a dynamic feature set of each display module, and carrying out external optical parameter monitoring and feature extraction on a plurality of display modules to obtain external optical influence feature components of each display module;

specifically, curve fitting is performed on the dynamic characteristic data of each display module to obtain a dynamic characteristic curve of each display module. A mathematical model is used to approximately describe the behavior patterns of these data. Curve fitting may reveal trends in the performance of the module under certain conditions, such as response at different frequencies or under different environments. The dynamic characteristic curve is subjected to characteristic point extraction, key data points are identified from the curve, and the points represent important characteristics of the curve, such as extreme points, inflection points and the like. The first curve characteristic points can accurately reflect the performance characteristics of the display module under specific conditions. And calculating a difference coefficient, and quantifying the performance difference of different modules or the same module under different conditions. The difference coefficient is a statistical index for measuring the degree of variation, and can reveal the variation range and the stability of the module characteristics. Based on the resulting target difference coefficients, the first curve feature points are feature classified, and the feature points are grouped for better understanding and use of the data. The feature classification may be based on different criteria, such as the type, size, or frequency of occurrence of feature points, etc. Such classification helps to more accurately understand the behavior pattern of each display module. And performing set conversion on the characteristic points of the second curve, and converting the characteristic points into a format which is more suitable for further analysis and processing, thereby forming a dynamic characteristic set of each display module. And monitoring external optical parameters of the display module. This includes measuring and recording various optical parameters, such as illumination intensity, color temperature, etc., which affect the performance of the display module. And then, extracting the characteristics, and identifying key factors influencing the performance of the display module from the external optical parameter data of each display module. By means of data analysis methods such as statistical analysis and pattern recognition, external optical influence characteristic components of each display module are constructed, and the characteristic components can help to better understand and predict the influence of external environments on the performance of the display module, so that key information is provided for the formulation of control strategies.

Step S104, performing display parameter analysis on a plurality of display modules according to the dynamic feature set and the external optical influence feature components by a multi-agent reinforcement learning algorithm to generate a first display parameter combination corresponding to each display module;

specifically, a target intelligent agent is built for each display module through a multi-intelligent agent reinforcement learning algorithm, and each target intelligent agent comprises an input layer, a decision layer and an output layer. The design of the target agent is to simulate and optimize the response and adjustment process of the display module. Each display module can be considered as a learning and adaptation entity that can self-adjust based on environmental feedback and internal characteristics. And carrying out feature coding on the dynamic feature set of each display module, and converting the dynamic feature set into dynamic feature vectors, wherein the feature coding is a process for converting actual physical and performance features into mathematical expressions. Similarly, the external optical influence characteristic components of each display module are subjected to characteristic vector conversion to obtain influence characteristic vectors. The conversion process ensures that the influence of external environmental factors such as illumination, temperature and the like on the performance of the display module can be fully considered in algorithm analysis. And inputting the dynamic characteristic vector and the influence characteristic vector of each display module into the corresponding target intelligent agent. At the input level of the agent, these vectors are fused to facilitate a more comprehensive and comprehensive analysis. Vector fusion is a process of data integration that aims to combine multiple data sources to provide more rich and comprehensive information. And carrying out display parameter analysis on the fusion feature vector through a plurality of decision trees in the decision layer. Decision trees are a common machine learning method, and data classification and prediction are performed by constructing a tree structure of decision rules. And analyzing the fusion feature vector through the decision tree, and outputting the initial display parameters of each tree. These initial display parameters represent the best display settings based on the current data. And carrying out parameter combination on the initial display parameters of the decision tree through an output layer of the intelligent agent to obtain a first display parameter combination corresponding to each display module, wherein various factors such as display effect, energy efficiency, environmental adaptability and the like are considered.

Step 105, performing display control on the plurality of display modules according to the first display parameter combination, collecting state feedback data corresponding to each display module, and performing parameter compensation strategy analysis on each display module based on the state feedback data corresponding to each display module to obtain a parameter compensation strategy corresponding to each display module;

specifically, display control is performed on the plurality of display modules according to the first display parameter combination. Including adjustment of parameters such as brightness, contrast, color balance, etc. In the process, the state of each display module is subjected to real-time data acquisition, and state feedback data corresponding to each display module is obtained. And then, carrying out characteristic analysis on the state feedback data, and analyzing the data acquired from each display module to identify key performance indexes such as brightness, color accuracy and response time. The brightness index reflects the light output intensity of the display module, the color accuracy relates to the accuracy of the color representation, and the response time describes the time required for the display module to change from receiving a signal to reacting. And carrying out parameter deviation calculation based on the performance index, and determining the difference between the actual performance and the expected performance of each display module. Calculation of the amount of parameter deviation may reveal which aspects of performance have not met predetermined criteria, as well as the specific values of these deviations. And calculating the compensation quantity and adjusting the dynamic compensation coefficient for the parameter deviation quantity of each display module. And determining the adjustment amplitude and the adjustment direction required under different conditions by calculating the parameter compensation range of each display module. Finally, the method includes the steps of. And creating a parameter compensation strategy of each display module according to the obtained parameter compensation range. This strategy is a comprehensive tuning scheme that takes into account the unique performance and environmental conditions of each module. By implementing the compensation strategy, it is ensured that each display module operates in an optimal state, maintaining an optimal display effect even in the face of constantly changing environmental conditions and use demands.

And S106, carrying out parameter optimization solving on the first display parameter combination based on a parameter compensation strategy, generating a second display parameter combination corresponding to each display module, and carrying out display control on the target display screen through the second display parameter combination corresponding to each display module by adopting a subdivision rectangular global optimization algorithm.

Specifically, a parameter optimization objective function for a first combination of display parameters is defined based on a parameter compensation strategy. The objective function must be capable of comprehensively reflecting performance targets of the display module, including key indexes such as brightness, color accuracy, response time, and the like. The definition of the objective function is a process of comprehensively considering a plurality of factors, and aims to find a group of parameter configurations so as to optimize the overall performance of the display module. And solving a plurality of parameter compensation ranges through a parameter optimization objective function, and finding out an optimal solution of each parameter compensation range. This solution process typically involves complex mathematical calculations, including iterative algorithms, gradient descent, or other optimization techniques. The aim is to find an optimal set of parameter configurations within a given parameter range that can meet all performance requirements while maintaining maximum efficiency and optimal display. And generating a second display parameter combination corresponding to each display module based on the optimal solution. The parameters of each display module are adjusted to ensure that they cooperate throughout the display system to provide consistent and high quality display. The generation of the second display parameter combination requires a comprehensive consideration of the characteristics of each module and the requirements of the entire display system. And searching the second display parameter combination corresponding to each display module by adopting a subdivision rectangular global optimization algorithm. The subdivision rectangular global optimization algorithm is an efficient global optimization method, and gradually approximates to a global optimal solution by continuously subdividing a parameter space and evaluating the performance of each subspace. In the process, display control is carried out on the target display screen according to a preset global optimization convergence criterion. The global optimization process ensures that each display module can operate in an optimal state within the whole display screen range, and finally the overall optimal display effect is realized.

In the embodiment of the application, the dynamic response test and the accurate analysis of the arrangement positions of the modules are carried out through the Newmark-beta algorithm, so that the optimal display effect of each display module at a specific position can be ensured. And the module display cooperative relation analysis and dynamic characteristic data analysis are combined, so that the whole display system can realize high synchronization among all modules, and the overall display quality is improved. The display parameters are analyzed by utilizing the multi-agent reinforcement learning algorithm, and the display parameters can be adjusted in real time based on environmental changes and module states, so that self-adaptive adjustment is realized. The collection of state feedback data and the analysis of parameter compensation strategies further enhance the adaptability of the system to external changes and the stability of display effects. The dynamic characteristics and external influences of each display module are accurately mastered through feature extraction and feature classification, so that resources can be utilized more effectively, and resource waste is avoided. And the display parameters are subjected to global optimization by adopting a subdivision rectangular global optimization algorithm, so that the efficient configuration and use of resources are realized on the premise of meeting the display requirements. The collected state feedback data and parameter compensation strategies not only can adjust the current state, but also can prevent potential display problems, and the stability and reliability of the system are enhanced. The stability of the system in long-term operation is further ensured by the aid of parameter optimization solving and the use of a global optimization algorithm, and maintenance cost and frequency are reduced. Through fine display module assembly control, can provide richer, clear and vivid visual effect, and then improved the rate of accuracy of display module assembly control.

In a specific embodiment, the process of executing step S101 may specifically include the following steps:

(1) Acquiring a plurality of display modules of a target display screen, and performing dynamic response test on the plurality of display modules based on a Newmark-beta algorithm to obtain an initial behavior data set of each display module;

(2) Respectively carrying out data cleaning on the initial behavior data set of each display module to obtain a first behavior data set of each display module;

(3) Performing outlier detection and removal on the first behavior data set of each display module respectively to obtain a second behavior data set of each display module;

(4) Respectively carrying out scale standardization processing on the second behavior data set of each display module to obtain a response behavior data set of each display module;

(5) And carrying out display module coding on the plurality of display modules to obtain a plurality of module coding values, and carrying out module arrangement analysis on the plurality of display modules according to the plurality of module coding values to obtain module arrangement positions corresponding to each display module.

Specifically, a plurality of display modules of a target display screen are obtained. And carrying out dynamic response test on the display module based on a Newmark-beta algorithm. The Newmark-beta algorithm is a dynamic numerical analysis method and is suitable for calculating the response of the display module under dynamic load. Through the test, initial behavior data sets of each display module are obtained, and the data sets contain information about response characteristics of the modules under different excitation. After the initial data set is obtained, the data of each display module are cleaned, so that the quality and usability of the data are improved. In the data cleaning process, irrelevant data needs to be removed, error data needs to be corrected, missing values need to be filled, and the like, so that the accuracy of subsequent analysis is ensured, and a first behavior data set of each display module is obtained after cleaning. Performing outlier detection and removal. Outliers refer to those outliers that differ significantly from most data, arising from various causes, such as sensor failure or external environmental disturbances. By removing these outliers, a more accurate and consistent second behavior data set may be obtained. And carrying out scale standardization processing on the second behavior data set of each display module. Scale normalization is the process of adjusting the range of different data sets to be comparable. For example, different modules may differ in brightness or color response due to design differences, and by normalization, these data may be made comparable in subsequent analysis. And after processing, obtaining a response behavior data set of each display module. And coding the display modules, and performing arrangement analysis on the display modules based on the codes. Display module encoding is a process that converts the physical and performance characteristics of the module into numbers or symbols, helping to more effectively identify and sort the modules in subsequent processing. The alignment analysis is to align the display modules based on the module codes to determine the optimal position of each module in the entire display screen. For example, the location of the module in the display may be determined based on the brightness, color rendering capability, response time, and the like of the module. In this way, each module is placed in a position that best exhibits its performance, thereby optimizing the display effect of the entire display screen.

In a specific embodiment, the process of executing step S102 may specifically include the following steps:

(1) Performing frequency response calculation on the plurality of display modules based on the response behavior data set to obtain a frequency response index of each display module;

(2) Performing stability calculation on the plurality of display modules based on the response behavior data set to obtain a stability index of each display module;

(3) Performing sensitivity calculation on the plurality of display modules based on the response behavior data set to obtain sensitivity indexes of each display module;

(4) Performing module display cooperative relation analysis on the frequency response index, the stability index and the sensitivity index of each display module according to the module arrangement positions to obtain a module display cooperative relation;

(5) And carrying out dynamic characteristic analysis on the plurality of display modules according to the module display cooperative relationship to obtain dynamic characteristic data of each display module.

Specifically, frequency response calculation is performed on a plurality of display modules based on the response behavior data set, response characteristics of each display module under different frequencies, such as brightness and color performance of the modules under different refresh rates, an effect of each module when processing a high-speed dynamic image is obtained, and frequency response indexes are obtained by analyzing the frequency response characteristics of each module, so that response capability of the modules to different frequency inputs is reflected. And (3) performing stability calculation, wherein the stability index evaluates the performance stability of each display module in long-time operation or under specific conditions. For example, in outdoor advertising display screen projects, the display module needs to maintain a stable display effect under different environmental conditions, such as strong light, high temperature or low temperature. And analyzing the response behavior data set, and evaluating the performance change of the module under the conditions to obtain the stability index. These indicators help identify performance degradation or failure trends, providing basis for maintenance and optimization. And performing sensitivity calculation on each display module. The sensitivity index reflects the degree of response of the module to changes in external variables. For example, in a display screen project with adaptive brightness adjustment, the display module needs to adjust its brightness according to the illumination change of the surrounding environment. And (3) determining the response speed and accuracy of each module to the environmental changes by analyzing the response behavior data set, and obtaining the sensitivity index. These metrics help to design highly adaptable and responsive display systems. And carrying out module display cooperative relation analysis on the frequency response index, the stability index and the sensitivity index of each display module according to the module arrangement positions, and understanding the interaction among different modules and how the interaction affects the overall display effect. For example, in a large multi-module tiled display screen project, the cooperative coordination among different modules is important for realizing the overall visual consistency, and the optimal coordination mode among the modules can be determined by analyzing the indexes of the different modules, so that the display effect is optimized. And according to the obtained module display cooperative relationship, carrying out dynamic characteristic analysis on the plurality of display modules to obtain dynamic characteristic data of each display module. All the previous analyses are integrated to obtain a comprehensive understanding of how each display module behaves in practical applications. This includes how the modules respond to various inputs, their performance under different operating conditions, and how they cooperate with other modules to achieve optimal performance of the overall display. Through comprehensive dynamic characteristic analysis, each module can be ensured to be in the optimal working state, so that the performance and efficiency of the whole display system are greatly improved.

In a specific embodiment, the process of executing step S103 may specifically include the following steps:

(1) Respectively performing curve fitting on the dynamic characteristic data of each display module to obtain a dynamic characteristic curve of each display module;

(2) Extracting curve characteristic points of dynamic characteristic curves of each display module respectively to obtain a plurality of first curve characteristic points of each display module;

(3) Calculating a difference coefficient of the dynamic characteristic curve of each display module to obtain a target difference coefficient;

(4) Performing feature classification on the plurality of first curve feature points according to the target difference coefficient to obtain a plurality of second curve feature points of each display module, and performing set conversion on the plurality of second curve feature points of each display module to obtain a dynamic feature set of each display module;

(5) Monitoring external optical parameters of the display modules to obtain external optical parameter data of each display module;

(6) And respectively carrying out feature extraction on the external optical parameter data of each display module and constructing external optical influence feature components of each display module.

Specifically, curve fitting is performed on dynamic characteristic data of each display module. Curve fitting is a mathematical tool used to find a mathematical function in a series of data points describing the trend of those data points. For example, if there is a display screen module whose brightness varies with the input signal, curve fitting may be used to build a model describing how brightness varies with the signal. This process may use a variety of mathematical models, such as linear models, polynomial models, or more complex nonlinear models, depending on the nature and complexity of the data. In this way, dynamic characteristics of each display module are obtained, which can reveal the performance of the module under different operating conditions. And extracting curve characteristic points of the dynamic characteristic curve of each display module. Feature point extraction is the identification and extraction of points in the curve that have important information, such as maxima, minima, or inflection points. For example, in a curve of color change response, the maximum value represents the maximum intensity of the color response, and the inflection point represents the location where the response begins to change. By extracting these first curve feature points, key performance indicators of each display module are obtained, and these indicators help to understand the performance characteristics of each module more deeply. And then, calculating a difference coefficient of the dynamic characteristic curve of each display module. The coefficient of difference is a statistical measure that measures the degree of variation of a set of data points from their average. And quantifying the consistency and reliability of the performance of each display module by calculating the difference coefficient. For example, a lower coefficient of difference indicates that the module exhibits relatively consistent performance under different conditions, while a higher coefficient of difference indicates that the performance varies more under different conditions. And carrying out feature classification on the plurality of first curve feature points according to the target difference coefficient. For example, the feature points are classified into different categories according to the performance variation of the display module at different brightness levels. And then, carrying out set conversion on a plurality of second curve characteristic points of each display module to obtain a dynamic characteristic set of each display module. And monitoring external optical parameters of the display modules, and extracting the characteristics of external optical parameter data of each display module. External optical parameter monitoring is to measure and record various optical parameters affecting the performance of the display module, such as ambient light intensity, color temperature, etc. For example, in an outdoor display project, the display module needs to maintain stable color performance under different daylight conditions. And (3) by monitoring the optical parameters and carrying out feature extraction on the data of each display module, constructing external optical influence feature components of each display module. These feature components can help understand and predict how the external environment affects the performance of each display module. For example, the display module needs to provide consistent visual effects under different indoor lighting conditions. By analyzing the external optical parameter data, it is determined which environmental factors have the greatest influence on the display performance, and the setting of the module is adjusted accordingly, so that a high-quality display effect can be provided under different illumination conditions.

In a specific embodiment, the process of executing step S104 may specifically include the following steps:

(1) Respectively constructing target intelligent agents of each display module by a multi-intelligent-agent reinforcement learning algorithm, wherein the target intelligent agents comprise an input layer, a decision layer and an output layer;

(2) Performing feature coding on the dynamic feature set of each display module to obtain a dynamic feature vector of each display module;

(3) Performing feature vector conversion on the external optical influence feature components of each display module to obtain influence feature vectors of each display module;

(4) Inputting the dynamic feature vector and the influence feature vector of each display module into the target intelligent agent of each display module respectively, and carrying out vector fusion on the dynamic feature vector and the influence feature vector through an input layer in the target intelligent agent to obtain a fusion feature vector;

(5) Performing display parameter analysis on the fusion feature vector through a plurality of decision trees in the decision layer to obtain initial display parameters of each decision tree;

(6) And carrying out parameter combination on the initial display parameters of each decision tree through an output layer in the target intelligent agent to obtain a first display parameter combination corresponding to each display module.

Specifically, the target agents of each display module are constructed, and the target agents comprise an input layer, a decision layer and an output layer. Each display module is regarded as an intelligent body capable of learning and self-adjusting, and the display module is gradually adapted to and optimizes the display effect through a reinforcement learning algorithm. For example, in a large outdoor LED screen project, each LED module may be configured as an agent that can autonomously adjust its display parameters to accommodate different ambient lighting conditions and content display requirements. And carrying out feature coding on the dynamic feature set of each display module to generate dynamic feature vectors. Feature encoding is the process of converting raw feature data into a format more suitable for machine processing and learning. These dynamic characteristics include the brightness response, color rendition capability, response speed, etc. of the module. By feature encoding, complex features are converted into mathematical vectors so that they can be efficiently processed by algorithms. And simultaneously, performing similar feature vector conversion on the external optical influence feature components of each display module. For example, the external optical influence characteristic components comprise ambient illumination intensity, illumination color temperature and the like, and all factors directly influence the performance of the display module. After the dynamic feature vector and the influencing feature vector of each display module are input to respective target intelligent agents, vector fusion is carried out through an input layer. Vector fusion is a process of data integration that combines information from the module's own dynamics and external environmental conditions to generate a comprehensive characterization. This fusion process ensures that all important information is taken into account, providing comprehensive data support for the next decisions. For example, an agent of an outdoor display module needs to comprehensively consider the brightness adjustment capability of the module and the current ambient light intensity to determine the optimal display parameters. At the decision layer, multiple decision trees are used to analyze the fused feature vectors and generate initial display parameters. Decision trees are a machine learning method, making decisions through a series of rules. Each decision tree evaluates different display parameter settings, such as brightness adjustment, color balance, etc., based on the fused feature vectors, thereby generating an initial set of display parameters. And carrying out further parameter combination on the initial display parameters through the output layer to form a first display parameter combination corresponding to each display module. Parameters obtained from each decision tree are synthesized and optimized to ensure that the best display effect is achieved on the whole display screen. For example, the output layer needs to coordinate the brightness and color settings of the different modules to ensure that a clear and consistent image is obtained from any angle of view.

In a specific embodiment, the process of executing step S105 may specifically include the following steps:

(1) Performing display control on the display modules according to the first display parameter combination, and performing state data acquisition on the display modules to obtain state feedback data corresponding to each display module;

(2) Performing characteristic analysis on the state feedback data to obtain brightness, color accuracy and response time corresponding to each display module;

(3) Calculating parameter deviation of each display module according to the brightness, color accuracy and response time corresponding to each display module, and obtaining a plurality of parameter deviation values corresponding to each display module;

(4) Calculating parameter compensation amounts and adjusting dynamic compensation coefficients for a plurality of parameter deviation amounts corresponding to each display module to obtain a plurality of parameter compensation ranges corresponding to each display module;

(5) And creating a parameter compensation strategy corresponding to each display module according to the plurality of parameter compensation ranges.

Specifically, display control is performed on the plurality of display modules according to the first display parameter combination. And applying the display parameters obtained through the multi-agent reinforcement learning algorithm to an actual display module. For example, the first display parameter combination of each module includes settings for a plurality of aspects of brightness, color balance, contrast, etc. After the parameters are applied, each module displays according to the preset values so as to achieve the best visual effect. And acquiring state data of the display modules to acquire real-time state feedback data of each module. The state data acquisition is a key monitoring process, and relates to real-time monitoring and recording of the performance of the display module in actual operation, wherein the data comprise key performance indexes such as brightness level, color performance, response speed and the like of the module. The state feedback data is subjected to feature analysis, and key performance indexes such as brightness level, color accuracy and response time are extracted from the acquired data. These indicators are important parameters for evaluating the performance of the display module, and can directly reflect the performance of the module in practical application. And calculating parameter deviation of each display module according to the analyzed performance index. The differences between the actual performance data and the expected performance targets are compared to determine a performance bias for each module. For example, if the actual brightness of a certain module is lower than the preset brightness, this will be recorded as a brightness deviation. And (3) knowing the difference between the performance of each module in terms of different performances and the expected targets through parameter deviation calculation. And calculating the parameter compensation quantity and adjusting the dynamic compensation coefficient according to the parameter deviation. Based on the identified performance bias, the necessary adjustment is determined to bring the performance of each module to or beyond the expected criteria. For example, by increasing the compensation brightness, those modules that exhibit less than normal brightness can be adjusted. The adjustment of the dynamic compensation coefficient is to adapt to the continuously changing environment and use condition, and ensure the consistency and accuracy of the display effect. In this way, a series of parameter compensation ranges are determined for each display module, which ranges specify the adjustment amplitude required for optimal performance. And creating a specific parameter compensation strategy for each display module according to the parameter compensation range. These strategies are tailored to the unique capabilities and requirements of each module, and take into account various factors such as the physical location of the module, the lighting conditions of the surrounding environment, the intended use scenario, etc. For example, for those modules that are directly exposed to sunlight, a higher brightness compensation range is required to ensure that the display is still clear under bright light conditions.

In a specific embodiment, the process of executing step S106 may specifically include the following steps:

(1) Defining a parameter optimization objective function of the first display parameter combination based on the parameter compensation strategy;

(2) Carrying out parameter optimization solution on a plurality of parameter compensation ranges through a parameter optimization objective function to obtain a parameter compensation optimal solution of each parameter compensation range;

(3) Generating a second display parameter combination corresponding to each display module according to the parameter compensation optimal solution of each parameter compensation range;

(4) Searching a second display parameter combination corresponding to each display module by adopting a subdivision rectangular global optimization algorithm, and performing display control on the target display screen according to a preset global optimization convergence criterion.

Specifically, a parameter optimization objective function of the first display parameter combination is defined based on the parameter compensation strategy, and the objective function determines how the display module adjusts the parameters thereof to achieve the optimal display effect. For example, optimizing the objective function may take into account factors such as brightness, color accuracy, response time of the module, and how these factors affect the viewing experience and visual effect of the display for the viewer. The objective function needs to comprehensively consider various aspects of display quality, energy efficiency, long-term stability and the like. And carrying out parameter optimization solving on the plurality of parameter compensation ranges through a parameter optimization objective function. And (3) finding out the optimal parameter configuration in the given compensation range through gradient descent, genetic algorithm or other optimization technologies to obtain the parameter compensation optimal solution of each parameter compensation range, and maintaining the highest efficiency and the best display effect while meeting all performance requirements. And generating a second display parameter combination corresponding to each display module according to the optimal solution of each parameter compensation range. And integrating and applying the parameter values to each display module. For example, the second combination of display parameters includes fine tuning of the brightness, color, and contrast of each module to ensure that clearly readable information is provided under different viewing conditions (e.g., different weather and lighting conditions). This process requires precise adjustment of the parameters of each display module to ensure that they work together throughout the display system, providing consistent and high quality display. And searching the second display parameter combination corresponding to each display module by adopting a subdivision rectangular global optimization algorithm. The subdivision rectangular global optimization algorithm is an efficient global optimization method, and gradually approximates to a global optimal solution by continuously subdividing a parameter space and evaluating the performance of each subspace. In the process, display control is carried out on the target display screen according to a preset global optimization convergence criterion.

The method for controlling the display module based on the artificial intelligence in the embodiment of the present application is described above, and the device for controlling the display module based on the artificial intelligence in the embodiment of the present application is described below, referring to fig. 2, one embodiment of the device for controlling the display module based on the artificial intelligence in the embodiment of the present application includes:

the acquisition module 201 is configured to acquire a plurality of display modules of a target display screen, perform a dynamic response test on the plurality of display modules based on a Newmark- β algorithm to obtain a response behavior data set of each display module, and perform module arrangement analysis on the plurality of display modules to obtain a module arrangement position corresponding to each display module;

the analysis module 202 is configured to perform module display cooperative relationship analysis on the plurality of display modules based on the response behavior data set and the module arrangement position to obtain a module display cooperative relationship, and perform dynamic characteristic analysis on the plurality of display modules according to the module display cooperative relationship to obtain dynamic characteristic data of each display module;

the feature extraction module 203 is configured to perform feature extraction and feature classification on the dynamic feature data of each display module to obtain a dynamic feature set of each display module, and perform external optical parameter monitoring and feature extraction on the plurality of display modules to obtain external optical influence feature components of each display module;

The processing module 204 is configured to perform display parameter analysis on the plurality of display modules according to the dynamic feature set and the external optical influence feature component through a multi-agent reinforcement learning algorithm, so as to generate a first display parameter combination corresponding to each display module;

the feedback module 205 is configured to perform display control on the plurality of display modules according to the first display parameter combination, collect status feedback data corresponding to each display module, and perform parameter compensation policy analysis on each display module based on the status feedback data corresponding to each display module, so as to obtain a parameter compensation policy corresponding to each display module;

and the solving module 206 is configured to perform parameter optimization solving on the first display parameter combination based on the parameter compensation policy, generate a second display parameter combination corresponding to each display module, and perform display control on the target display screen through the second display parameter combination corresponding to each display module by adopting a subdivision rectangular global optimization algorithm.

Through the cooperation of the components, dynamic response test and accurate analysis of the arrangement positions of the modules are carried out through a Newmark-beta algorithm, so that the optimal display effect of each display module at a specific position can be ensured. And the module display cooperative relation analysis and dynamic characteristic data analysis are combined, so that the whole display system can realize high synchronization among all modules, and the overall display quality is improved. The display parameters are analyzed by utilizing the multi-agent reinforcement learning algorithm, and the display parameters can be adjusted in real time based on environmental changes and module states, so that self-adaptive adjustment is realized. The collection of state feedback data and the analysis of parameter compensation strategies further enhance the adaptability of the system to external changes and the stability of display effects. The dynamic characteristics and external influences of each display module are accurately mastered through feature extraction and feature classification, so that resources can be utilized more effectively, and resource waste is avoided. And the display parameters are subjected to global optimization by adopting a subdivision rectangular global optimization algorithm, so that the efficient configuration and use of resources are realized on the premise of meeting the display requirements. The collected state feedback data and parameter compensation strategies not only can adjust the current state, but also can prevent potential display problems, and the stability and reliability of the system are enhanced. The stability of the system in long-term operation is further ensured by the aid of parameter optimization solving and the use of a global optimization algorithm, and maintenance cost and frequency are reduced. Through fine display module assembly control, can provide richer, clear and vivid visual effect, and then improved the rate of accuracy of display module assembly control.

The application also provides a chip for executing the steps of the artificial intelligence-based display module control method in the above embodiments.

The application further provides a computer readable storage medium, which may be a nonvolatile computer readable storage medium, or may be a volatile computer readable storage medium, where instructions are stored in the computer readable storage medium, when the instructions run on a computer, cause the computer to execute the steps of the artificial intelligence-based display module control method.

It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, systems and units may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random acceS memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The above embodiments are merely for illustrating the technical solution of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.

Claims

1. The display module control method based on the artificial intelligence is characterized by comprising the following steps of:

2. The method for controlling display modules based on artificial intelligence according to claim 1, wherein the steps of obtaining a plurality of display modules of a target display screen, performing a dynamic response test on the plurality of display modules based on a Newmark- β algorithm to obtain a response behavior data set of each display module, and performing a module arrangement analysis on the plurality of display modules to obtain a module arrangement position corresponding to each display module, include:

acquiring a plurality of display modules of a target display screen, and performing dynamic response test on the plurality of display modules based on a Newmark-beta algorithm to obtain an initial behavior data set of each display module;

respectively carrying out data cleaning on the initial behavior data set of each display module to obtain a first behavior data set of each display module;

performing outlier detection and removal on the first behavior data set of each display module respectively to obtain a second behavior data set of each display module;

respectively carrying out scale standardization processing on the second behavior data set of each display module to obtain a response behavior data set of each display module;

and carrying out display module coding on the plurality of display modules to obtain a plurality of module coding values, and carrying out module arrangement analysis on the plurality of display modules according to the plurality of module coding values to obtain module arrangement positions corresponding to each display module.

3. The method according to claim 1, wherein the performing module display cooperative relationship analysis on the plurality of display modules based on the response behavior data set and the module arrangement position to obtain a module display cooperative relationship, and performing dynamic characteristic analysis on the plurality of display modules according to the module display cooperative relationship to obtain dynamic characteristic data of each display module, includes:

performing frequency response calculation on the plurality of display modules based on the response behavior data set to obtain a frequency response index of each display module;

performing stability calculation on the plurality of display modules based on the response behavior data set to obtain a stability index of each display module;

performing sensitivity calculation on the plurality of display modules based on the response behavior data set to obtain sensitivity indexes of each display module;

performing module display cooperative relation analysis on the frequency response index, the stability index and the sensitivity index of each display module according to the module arrangement positions to obtain a module display cooperative relation;

and carrying out dynamic characteristic analysis on the plurality of display modules according to the module display cooperative relationship to obtain dynamic characteristic data of each display module.

4. The method for controlling display modules based on artificial intelligence according to claim 1, wherein the performing feature extraction and feature classification on the dynamic characteristic data of each display module to obtain a dynamic feature set of each display module, and performing external optical parameter monitoring and feature extraction on the plurality of display modules to obtain external optical influence feature components of each display module comprises:

respectively performing curve fitting on the dynamic characteristic data of each display module to obtain a dynamic characteristic curve of each display module;

extracting curve characteristic points of dynamic characteristic curves of each display module respectively to obtain a plurality of first curve characteristic points of each display module;

calculating a difference coefficient of the dynamic characteristic curve of each display module to obtain a target difference coefficient;

performing feature classification on the first curve feature points according to the target difference coefficient to obtain second curve feature points of each display module, and performing set conversion on the second curve feature points of each display module to obtain a dynamic feature set of each display module;

monitoring external optical parameters of the display modules to obtain external optical parameter data of each display module;

And respectively carrying out feature extraction on the external optical parameter data of each display module and constructing external optical influence feature components of each display module.

5. The method according to claim 1, wherein the performing, by the multi-agent reinforcement learning algorithm, display parameter analysis on the plurality of display modules according to the dynamic feature set and the external optical influence feature component, and generating a first display parameter combination corresponding to each display module, includes:

respectively constructing target intelligent agents of each display module by a multi-intelligent-agent reinforcement learning algorithm, wherein the target intelligent agents comprise an input layer, a decision layer and an output layer;

performing feature coding on the dynamic feature set of each display module to obtain a dynamic feature vector of each display module;

performing feature vector conversion on the external optical influence feature components of each display module to obtain influence feature vectors of each display module;

inputting the dynamic feature vector and the influence feature vector of each display module into a target intelligent agent of each display module respectively, and carrying out vector fusion on the dynamic feature vector and the influence feature vector through an input layer in the target intelligent agent to obtain a fusion feature vector;

Performing display parameter analysis on the fusion feature vector through a plurality of decision trees in the decision layer to obtain initial display parameters of each decision tree;

and carrying out parameter combination on the initial display parameters of each decision tree through an output layer in the target intelligent agent to obtain a first display parameter combination corresponding to each display module.

6. The method of claim 1, wherein the performing display control on the plurality of display modules according to the first display parameter combination and collecting status feedback data corresponding to each display module, and performing parameter compensation policy analysis on each display module based on the status feedback data corresponding to each display module, to obtain a parameter compensation policy corresponding to each display module, includes:

performing display control on the plurality of display modules according to the first display parameter combination, and performing state data acquisition on the plurality of display modules to obtain state feedback data corresponding to each display module;

performing characteristic analysis on the state feedback data to obtain brightness, color accuracy and response time corresponding to each display module;

Calculating parameter deviation of each display module according to the brightness, color accuracy and response time corresponding to each display module, and obtaining a plurality of parameter deviation values corresponding to each display module;

calculating parameter compensation amounts and adjusting dynamic compensation coefficients for a plurality of parameter deviation amounts corresponding to each display module to obtain a plurality of parameter compensation ranges corresponding to each display module;

and creating a parameter compensation strategy corresponding to each display module according to the parameter compensation ranges.

7. The method for controlling a display module based on artificial intelligence according to claim 6, wherein the performing parameter optimization solution on the first display parameter combination based on the parameter compensation strategy to generate a second display parameter combination corresponding to each display module, and performing display control on the target display screen through the second display parameter combination corresponding to each display module by using a subdivision rectangular global optimization algorithm, includes:

defining a parameter optimization objective function for the first combination of display parameters based on the parameter compensation strategy;

carrying out parameter optimization solving on the plurality of parameter compensation ranges through the parameter optimization objective function to obtain a parameter compensation optimal solution of each parameter compensation range;

Generating a second display parameter combination corresponding to each display module according to the parameter compensation optimal solution of each parameter compensation range;

searching a second display parameter combination corresponding to each display module by adopting a subdivision rectangular global optimization algorithm, and performing display control on the target display screen according to a preset global optimization convergence criterion.

8. Display module controlling means based on artificial intelligence, its characterized in that, display module controlling means based on artificial intelligence includes:

9. A chip for performing the artificial intelligence based display module control method according to any one of claims 1-7.

10. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the artificial intelligence based display module control method of any of claims 1-7.