A liquid crystal screen data optimization management system and method based on big data analysis

Abstract

The present invention relates to the technical field of liquid crystal screen data management, and specifically to a liquid crystal screen data optimization management system and method based on big data analysis, comprising analyzing the correlation between a liquid crystal screen operating parameter and a target liquid crystal color cast parameter of a liquid crystal screen to obtain liquid crystal screen operating parameter related data; using the least squares method to estimate the model parameters of the liquid crystal screen in an ARIMA model, and constructing a liquid crystal screen color cast optimization model according to the obtained target liquid crystal screen performance reference data; predicting the working condition of the liquid crystal screen to obtain liquid crystal screen color cast prediction data, calibrating and optimizing the liquid crystal screen color cast prediction data to obtain target liquid crystal screen color cast prediction data; obtaining the target liquid crystal screen color cast prediction data of the liquid crystal screen, obtaining the color calibration data of the liquid crystal screen, and optimizing the color display of the liquid crystal screen based on the color calibration data, and uploading the related data to a cloud server.

Description

Technical Field

[0001] The present invention relates to the technical field of liquid crystal screen data management, and in particular to a liquid crystal screen data optimization management system and method based on big data analysis. Background Art

[0002] As people's consumption level improves, their requirements for display devices are getting higher and higher. TFT display devices have been widely used because they can provide high-resolution images, clear display details and bright colors. However, the TFT transistors in TFT display devices will have a half-life due to their own material problems. After the TFT display device has been used for a long time, the TF transistors in the TFT display device will decay, resulting in color deviation in the TFT display device, affecting customer use.

[0003] In order to solve the above problems, the usual practice is to add a screen protection function through an application program, and to add a screen-off function when the user is not using the TFT display device. Although this approach extends the service life of the LCD screen, it requires the user to wake up the screen by himself or the sensor to detect and wake up the screen to exit the screen-off state. However, this approach will not only cause inconvenience to the user's operation, but may also increase costs due to the addition of sensors. At the same time, this approach is obviously not applicable to the use environment where the LCD screen needs to be always on. In order to solve the problem in the use environment where the LCD screen needs to be always on, there is another solution, which is to use better transistors in the TFT device. However, although this solution increases the service life of the LCD screen in the TFT display device, it also greatly increases the cost of the equipment, and because of the extremely high requirements for transistors, it will also easily lead to an increase in the defective rate. Summary of the invention

[0004] The purpose of the present invention is to provide a liquid crystal screen data optimization management system and method based on big data analysis to solve the problems existing in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for optimizing and managing LCD screen data based on big data analysis, the method comprising:

[0006] Step S100: obtaining historical color cast adjustment experiment records of the LCD screen, obtaining LCD screen color cast adjustment experiment data from the historical color cast adjustment experiment records, analyzing the correlation between the LCD screen operating parameters and the target LCD color cast parameters of the LCD screen, and obtaining LCD screen operating parameter related data;

[0007] Step S200: based on the historical color cast adjustment experiment record of the LCD screen, the autocorrelation function graph and the partial autocorrelation function graph are plotted, and the relevant order of the ARIMA model is obtained by combining the relevant data of the LCD screen operation parameters, and the model parameters of the LCD screen in the ARIMA model are estimated by the least squares method, and the LCD screen color cast optimization model is constructed according to the obtained target LCD screen performance reference data;

[0008] Step S300: using the screen drive chip SOC to collect the LCD screen operating parameters of the LCD screen, and inputting the collected LCD screen operating parameters into the LCD screen color cast optimization model, predicting the working conditions of the LCD screen to obtain LCD screen color cast prediction data, obtaining historical LCD screen color cast prediction records from the cloud server, and calibrating and optimizing the LCD screen color cast prediction data based on the historical LCD screen color cast prediction records to obtain target LCD screen color cast prediction data;

[0009] Step S400: Obtain target LCD color cast prediction data of the LCD screen, obtain color calibration data of the LCD screen based on the target LCD color cast prediction data, optimize the LCD color display based on the color calibration data, and upload relevant data to the cloud server.

[0010] Furthermore, step S100 includes:

[0011] Step S101: acquiring historical color cast adjustment experiment records of the LCD screen from the cloud platform, and acquiring LCD screen color cast adjustment experiment data from the historical color cast adjustment experiment records, wherein the LCD screen color cast adjustment experiment data includes data corresponding to various LCD screen operating parameters and target LCD color cast parameters of the LCD screen;

[0012] Step S102: acquiring the time point at which each historical color cast adjustment experiment record is acquired by the cloud platform, and sorting each historical color cast adjustment experiment record according to the time sequence;

[0013] Step S103: analyzing the correlation between the LCD screen operating parameters and the target LCD color cast parameters of the LCD screen, wherein the specific analysis process of the correlation between the a-th LCD screen operating parameter and the target LCD color cast parameter is to obtain the value of the a-th LCD screen operating parameter in each historical color cast adjustment experiment record, and rank the a-th LCD screen operating parameter in each historical color cast adjustment experiment record according to the value, obtain the rank of the a-th LCD screen operating parameter in a certain historical color cast adjustment experiment record, and use the ranked value as the parameter order value of the a-th LCD screen operating parameter in a certain historical color cast adjustment experiment record;

[0014] Step S104: Calculate the correlation strength value U between the a-th LCD screen operating parameter and the target liquid crystal color cast parametera :

[0015]

[0016] Among them, X a,i It is represented as the parameter order value of the a-th LCD screen operating parameter in the i-th historical color cast adjustment experiment record; Y i It is represented as the target liquid crystal color cast parameter, the parameter order value in the i-th historical color cast adjustment experiment record; n is the total number of each historical color cast adjustment experiment record;

[0017] Step S105: when the correlation strength value between the a-th LCD screen operating parameter and the target LCD color cast parameter is greater than a preset first correlation strength threshold, it is determined that there is a positive monotonic correlation between the a-th LCD screen operating parameter and the target LCD color cast parameter, and the a-th LCD screen operating parameter is marked;

[0018] Step S106: when the correlation strength value between the a-th LCD screen operating parameter and the target LCD color cast parameter is less than the preset second correlation strength threshold, it is determined that there is a negative monotonic correlation between the a-th LCD screen operating parameter and the target LCD color cast parameter, wherein the first correlation strength threshold is greater than the second correlation strength threshold, and the a-th LCD screen operating parameter is marked;

[0019] Step S107: acquiring a plurality of LCD screen operating parameters marked in the LCD screen, and collecting the plurality of LCD screen operating parameters to obtain LCD screen operating parameter related data.

[0020] Further, step S200 includes:

[0021] Step S201: obtaining various historical color cast adjustment experimental records of the LCD screen, drawing an autocorrelation function diagram and a partial autocorrelation function diagram based on the various historical color cast adjustment experimental records, and analyzing the correlation function diagram and the partial autocorrelation function diagram in combination with relevant data of LCD screen operation parameters to obtain various relevant orders of the ARIMA model of the LCD screen;

[0022] Step S202: using the least squares method to estimate the model parameters of the ARIMA model to obtain the ARIMA model of the LCD screen;

[0023] Step S203: Obtain target LCD performance reference data of the LCD screen from the cloud platform, perform statistical induction on the performance data of the LCD screen based on the target LCD performance reference data, and input the data into the ARIMA model of the LCD screen for model construction, so as to obtain the optimization model data of the LCD screen color cast optimization model.

[0024] Furthermore, step S300 includes:

[0025] Step S301: converting the LCD screen color cast optimization model through RKNN and running it in the NPU in the screen display driver chip SOC;

[0026] Step S302: using the screen drive chip SOC, collecting various LCD screen operating parameters of the LCD screen in the current cycle, obtaining data corresponding to the various LCD screen operating parameters, and inputting the obtained various LCD screen operating parameters of the LCD screen into the LCD screen color cast optimization model, predicting the LCD screen working condition, and obtaining LCD screen color cast prediction data of the LCD screen;

[0027] Step S303: acquiring each historical LCD color cast prediction record of the stored LCD screen from the cloud server, and acquiring data corresponding to a plurality of marked LCD screen operating parameters and target LCD color cast parameters in the LCD screen from the historical LCD color cast prediction records;

[0028] Step S304: based on the historical LCD color cast prediction record, verify and optimize the LCD color cast prediction data of the LCD in the current cycle, and obtain the absolute value of the difference between the marked several items of LCD operating parameters in the historical LCD color cast prediction record and the average value of several items of LCD operating parameters in the LCD in the current cycle;

[0029] Step S305: when the absolute values ​​of the differences between several items of LCD screen operating parameters in a certain historical LCD screen color cast prediction record and the average values ​​of several items of LCD screen operating parameters in the LCD screen in the current cycle are all less than a preset characteristic threshold, the certain historical LCD screen color cast prediction record is recorded as a reference historical LCD screen color cast prediction record;

[0030] Step S306: Obtain each comparison history LCD color cast prediction record of the LCD screen in the current cycle, and obtain the average value μ of the target LCD color cast parameter in each comparison history LCD color cast prediction record, and calculate the predicted abnormal value Y of the LCD color cast prediction data of the LCD screen in the current cycle:

[0031]

[0032] Wherein, X represents the average value of the target liquid crystal color cast parameter in the liquid crystal screen color cast prediction data in the current cycle; σ represents the standard deviation of the target liquid crystal color cast parameter in each comparison historical liquid crystal screen color cast prediction record;

[0033] Step S307: when the predicted abnormal value Y is greater than the preset predicted abnormal threshold, it is determined that the LCD screen color cast prediction data of the LCD screen in the current cycle has a problem, and the LCD screen color cast prediction data is optimized and adjusted according to the comparison historical LCD screen color cast prediction records of the LCD screen in the current cycle to obtain the target LCD screen color cast prediction data; otherwise, when the predicted abnormal value Y is less than or equal to the preset predicted abnormal threshold, the LCD screen color cast prediction data is recorded as the target LCD screen color cast prediction data;

[0034] The RKNN in the above steps is a tool that converts the results of server-side calculations to the chip side for deployment. A large model is obtained based on a large amount of cloud computing. It can be deployed to the NPU of the screen driver chip SOC through RKNN for end-side computing operations. This method can work without communicating with the cloud server, thereby greatly improving the computing efficiency of the screen driver chip SOC.

[0035] Furthermore, step S400 includes:

[0036] Step S401: acquiring target LCD color cast prediction data of the LCD in the current cycle, and obtaining color calibration data K of the LCD in the current cycle using an LCD color cast optimization model based on the target LCD color cast prediction data, wherein K=F+S, F is color uncalibrated data, and S is a module prediction supplement value of the LCD color cast optimization model;

[0037] Step S402: The screen driver chip S0C in the LCD screen performs color superposition based on the color calibration data of the LCD screen in the current cycle, and transmits the RGB signal to the LCD screen for display. The NPU in the screen driver chip S0C uploads the target LCD screen color cast prediction data predicted by the LCD screen color cast optimization model to the cloud server, and verifies and remotely updates the model data of the LCD screen color cast optimization model.

[0038] In order to better implement the above method, an LCD screen data optimization management system is also proposed, which includes a correlation analysis module, a model building module, a target prediction module, and a display optimization module;

[0039] A correlation analysis module is used to analyze the correlation between the LCD screen operating parameters and the target LCD color cast parameters in the LCD screen color cast adjustment experimental data, and obtain LCD screen operating parameter correlation data of the target LCD color cast parameters;

[0040] A model building module is used to build a color cast optimization model for a liquid crystal screen according to the obtained target liquid crystal screen performance reference data, so as to obtain a color cast optimization model for a liquid crystal screen;

[0041] A target prediction module is used to predict the working condition of the LCD screen, obtain the LCD screen color cast prediction data, obtain the historical LCD screen color cast prediction records stored from the cloud server, calibrate and optimize the LCD screen color cast prediction data based on the historical LCD screen color cast prediction records, and obtain the target LCD screen color cast prediction data;

[0042] The display optimization module is used to obtain the color calibration data of the LCD screen according to the target LCD screen color cast prediction data, optimize the LCD screen color display based on the color calibration data, and upload the relevant data to the cloud server.

[0043] Further, the correlation analysis module includes a correlation intensity value unit and a LCD screen operation parameter related data unit;

[0044] A correlation strength value unit, used to calculate the correlation strength value between each LCD screen operating parameter and the target LCD color cast parameter;

[0045] The LCD screen operating parameter related data unit is used to obtain several LCD screen operating parameters marked in the LCD screen, and to collect several LCD screen operating parameters to obtain LCD screen operating parameter related data of the target LCD color cast parameter.

[0046] Further, the model building module includes a model building unit;

[0047] The model building unit is used to obtain the target LCD screen performance reference data of the LCD screen from the cloud platform, statistically summarize the performance data of the LCD screen according to the target LCD screen performance reference data, and enter it into the ARIMA model of the LCD screen for model building to obtain the LCD screen color cast optimization model.

[0048] Further, the target prediction module includes a liquid crystal screen color cast prediction data unit and a target liquid crystal screen color cast prediction data unit;

[0049] The LCD color cast prediction data unit is used to collect various LCD operating parameters of the LCD in the current cycle, obtain data corresponding to the various LCD operating parameters, and input the obtained various LCD operating parameters of the LCD into the LCD color cast optimization model to predict the LCD working condition and obtain the LCD color cast prediction data of the LCD;

[0050] The target LCD color cast prediction data unit is used to verify and optimize the LCD color cast prediction data of the LCD screen in the current cycle according to the historical LCD color cast prediction records, so as to obtain the target LCD color cast prediction data of the LCD screen in the current cycle.

[0051] Further, the display optimization module includes an optimization management unit;

[0052] The optimization management unit is used to obtain the target LCD color cast prediction data of the LCD screen in the current cycle, and use the LCD color cast optimization model based on the target LCD color cast prediction data to obtain the calibrated color data of the LCD screen in the current cycle, perform color superposition based on the calibrated color data, and transmit the RGB signal to the LCD screen for display. The NPU in the screen driver chip S0C uploads the target LCD color cast prediction data predicted by the LCD color cast optimization model to the cloud server, and verifies and remotely updates the model data of the LCD color cast optimization model.

[0053] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention realizes adjustment of the color display setting of the LCD screen according to the acquired LCD screen data, thereby solving the color cast problem of the LCD screen caused by long-term use, and when adjusting the color cast, the prediction results obtained by the model can be calibrated and optimized according to historical data, which greatly improves the accuracy of color calibration. At the same time, when adjusting the color cast of the LCD screen, there is no need to replace the transistors of the LCD screen, which also reduces the manufacturing cost of the LCD screen. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings are used to provide a further understanding of the present invention and constitute part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0055] Figure 1 It is a method flow chart of a liquid crystal screen data optimization management system and method based on big data analysis of the present invention;

[0056] Figure 2 It is a module schematic diagram of a liquid crystal screen data optimization management system and method based on big data analysis of the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] See also Figure 1-Figure 2 The present invention provides a technical solution: a method for optimizing and managing LCD screen data based on big data analysis, the method comprising:

[0059] Step S100: obtaining historical color cast adjustment experiment records of the LCD screen, obtaining LCD screen color cast adjustment experiment data from the historical color cast adjustment experiment records, analyzing the correlation between the LCD screen operating parameters and the target LCD color cast parameters of the LCD screen, and obtaining LCD screen operating parameter related data;

[0060] Wherein, step S100 includes:

[0061] Step S101: acquiring historical color cast adjustment experiment records of the LCD screen from the cloud platform, and acquiring LCD screen color cast adjustment experiment data from the historical color cast adjustment experiment records, wherein the LCD screen color cast adjustment experiment data includes data corresponding to various LCD screen operating parameters and target LCD color cast parameters of the LCD screen;

[0062] For example, various LCD screen operating parameters include the temperature, current, and voltage of the LCD screen;

[0063] Step S102: acquiring the time point at which each historical color cast adjustment experiment record is acquired by the cloud platform, and sorting each historical color cast adjustment experiment record according to the time sequence;

[0064] Step S103: analyzing the correlation between the LCD screen operating parameters and the target LCD color cast parameters of the LCD screen, wherein the specific analysis process of the correlation between the a-th LCD screen operating parameter and the target LCD color cast parameter is to obtain the value of the a-th LCD screen operating parameter in each historical color cast adjustment experiment record, and rank the a-th LCD screen operating parameter in each historical color cast adjustment experiment record according to the value, obtain the rank of the a-th LCD screen operating parameter in a certain historical color cast adjustment experiment record, and use the ranked value as the parameter order value of the a-th LCD screen operating parameter in a certain historical color cast adjustment experiment record;

[0065] Step S104: Calculate the correlation strength value U between the a-th LCD screen operating parameter and the target liquid crystal color cast parameter a :

[0066]

[0067] Among them, X a,i It is represented as the parameter order value of the a-th LCD screen operating parameter in the i-th historical color cast adjustment experiment record; Y i It is represented as the target liquid crystal color cast parameter, the parameter order value in the i-th historical color cast adjustment experiment record; n is the total number of each historical color cast adjustment experiment record;

[0068] Step S105: when the correlation strength value between the a-th LCD screen operating parameter and the target LCD color cast parameter is greater than a preset first correlation strength threshold, it is determined that there is a positive monotonic correlation between the a-th LCD screen operating parameter and the target LCD color cast parameter, and the a-th LCD screen operating parameter is marked;

[0069] Step S106: when the correlation strength value between the a-th LCD screen operating parameter and the target LCD color cast parameter is less than the preset second correlation strength threshold, it is determined that there is a negative monotonic correlation between the a-th LCD screen operating parameter and the target LCD color cast parameter, wherein the first correlation strength threshold is greater than the second correlation strength threshold, and the a-th LCD screen operating parameter is marked;

[0070] Step S107: obtaining a plurality of LCD screen operating parameters marked in the LCD screen, and collecting the plurality of LCD screen operating parameters to obtain LCD screen operating parameter related data;

[0071] Step S200: based on the historical color cast adjustment experiment record of the LCD screen, the autocorrelation function graph and the partial autocorrelation function graph are plotted, and the relevant order of the ARIMA model is obtained by combining the relevant data of the LCD screen operation parameters, and the model parameters of the LCD screen in the ARIMA model are estimated by the least squares method, and the LCD screen color cast optimization model is constructed according to the obtained target LCD screen performance reference data;

[0072] Wherein, step S200 includes:

[0073] Step S201: obtaining various historical color cast adjustment experimental records of the LCD screen, drawing an autocorrelation function diagram and a partial autocorrelation function diagram based on the various historical color cast adjustment experimental records, and analyzing the correlation function diagram and the partial autocorrelation function diagram in combination with relevant data of LCD screen operation parameters to obtain various relevant orders of the ARIMA model of the LCD screen;

[0074] Step S202: using the least squares method to estimate the model parameters of the ARIMA model to obtain the ARIMA model of the LCD screen;

[0075] Step S203: Obtain target LCD performance reference data of the LCD from the cloud platform, perform statistical induction on the performance data of the LCD based on the target LCD performance reference data, and input the data into the ARIMA model of the LCD to build the model, so as to obtain the optimization model data of the LCD color cast optimization model;

[0076] Step S300: using the screen drive chip SOC to collect the LCD screen operating parameters of the LCD screen, and inputting the collected LCD screen operating parameters into the LCD screen color cast optimization model, predicting the working conditions of the LCD screen to obtain LCD screen color cast prediction data, obtaining historical LCD screen color cast prediction records from the cloud server, and calibrating and optimizing the LCD screen color cast prediction data based on the historical LCD screen color cast prediction records to obtain target LCD screen color cast prediction data;

[0077] Wherein, step S300 includes:

[0078] Step S301: converting the LCD screen color cast optimization model through RKNN and running it in the NPU in the screen display driver chip SOC;

[0079] Step S302: using the screen drive chip SOC, collecting various LCD screen operating parameters of the LCD screen in the current cycle, obtaining data corresponding to the various LCD screen operating parameters, and inputting the obtained various LCD screen operating parameters of the LCD screen into the LCD screen color cast optimization model, predicting the LCD screen working condition, and obtaining LCD screen color cast prediction data of the LCD screen;

[0080] Step S303: acquiring each historical LCD color cast prediction record of the stored LCD screen from the cloud server, and acquiring data corresponding to a plurality of marked LCD screen operating parameters and target LCD color cast parameters in the LCD screen from the historical LCD color cast prediction records;

[0081] Step S304: based on the historical LCD color cast prediction record, verify and optimize the LCD color cast prediction data of the LCD in the current cycle, and obtain the absolute value of the difference between the marked several items of LCD operating parameters in the historical LCD color cast prediction record and the average value of several items of LCD operating parameters in the LCD in the current cycle;

[0082] Step S305: when the absolute values ​​of the differences between several items of LCD screen operating parameters in a certain historical LCD screen color cast prediction record and the average values ​​of several items of LCD screen operating parameters in the LCD screen in the current cycle are all less than a preset characteristic threshold, the certain historical LCD screen color cast prediction record is recorded as a reference historical LCD screen color cast prediction record;

[0083] Step S306: Obtain each comparison history LCD color cast prediction record of the LCD screen in the current cycle, and obtain the average value μ of the target LCD color cast parameter in each comparison history LCD color cast prediction record, and calculate the predicted abnormal value Y of the LCD color cast prediction data of the LCD screen in the current cycle:

[0084]

[0085] Wherein, X represents the average value of the target liquid crystal color cast parameter in the liquid crystal screen color cast prediction data in the current cycle; σ represents the standard deviation of the target liquid crystal color cast parameter in each comparison historical liquid crystal screen color cast prediction record;

[0086] Step S307: when the predicted abnormal value Y is greater than the preset predicted abnormal threshold, it is determined that the LCD screen color cast prediction data of the LCD screen in the current cycle has a problem, and the LCD screen color cast prediction data is optimized and adjusted according to the comparison historical LCD screen color cast prediction records of the LCD screen in the current cycle to obtain the target LCD screen color cast prediction data; otherwise, when the predicted abnormal value Y is less than or equal to the preset predicted abnormal threshold, the LCD screen color cast prediction data is recorded as the target LCD screen color cast prediction data;

[0087] Step S400: acquiring target LCD color cast prediction data of the LCD screen, acquiring color calibration data of the LCD screen based on the target LCD color cast prediction data, optimizing the LCD color display based on the color calibration data, and uploading the relevant data to the cloud server;

[0088] Wherein, step S400 includes:

[0089] Step S401: acquiring target LCD color cast prediction data of the LCD in the current cycle, and obtaining color calibration data K of the LCD in the current cycle using an LCD color cast optimization model based on the target LCD color cast prediction data, wherein K=F+S, F is color uncalibrated data, and S is a module prediction supplement value of the LCD color cast optimization model;

[0090] For example, the color uncalibrated data of the LCD screen is uploaded to the display screen through the application. For example, the application now displays a pure red, that is, RBG = 0Xff0000, then the screen displays the color according to 0XFF0000. When calculated by the NPU, K = 0XFF0000 + S;

[0091] Step S402: the screen driver chip S0C in the LCD screen performs color superposition based on the color calibration data of the LCD screen in the current cycle, and transmits the RGB signal to the LCD screen for display. The NPU in the screen driver chip S0C uploads the target LCD screen color cast prediction data predicted by the LCD screen color cast optimization model to the cloud server, and verifies and remotely updates the model data of the LCD screen color cast optimization model.

[0092] In order to better implement the above method, an LCD screen data optimization management system is also proposed, which includes a correlation analysis module, a model building module, a target prediction module, and a display optimization module;

[0093] A correlation analysis module is used to analyze the correlation between the LCD screen operating parameters and the target LCD color cast parameters in the LCD screen color cast adjustment experimental data, and obtain LCD screen operating parameter correlation data of the target LCD color cast parameters;

[0094] A model building module is used to build a color cast optimization model for a liquid crystal screen according to the obtained target liquid crystal screen performance reference data, so as to obtain a color cast optimization model for a liquid crystal screen;

[0095] A target prediction module is used to predict the working condition of the LCD screen, obtain the LCD screen color cast prediction data, obtain the historical LCD screen color cast prediction records stored from the cloud server, calibrate and optimize the LCD screen color cast prediction data based on the historical LCD screen color cast prediction records, and obtain the target LCD screen color cast prediction data;

[0096] A display optimization module is used to obtain the color calibration data of the LCD screen according to the color cast prediction data of the target LCD screen, optimize the color display of the LCD screen based on the color calibration data, and upload the relevant data to the cloud server;

[0097] Among them, the correlation analysis module includes a correlation intensity value unit and a LCD screen operation parameter related data unit;

[0098] A correlation strength value unit, used to calculate the correlation strength value between each LCD screen operating parameter and the target LCD color cast parameter;

[0099] The LCD screen operation parameter related data unit is used to obtain a number of LCD screen operation parameters marked in the LCD screen, and to collect the several LCD screen operation parameters to obtain the LCD screen operation parameter related data of the target LCD color cast parameter;

[0100] Wherein, the model building module includes a model building unit;

[0101] A model building unit is used to obtain target LCD performance reference data of the LCD screen from the cloud platform, statistically summarize the performance data of the LCD screen according to the target LCD performance reference data, and enter the data into the ARIMA model of the LCD screen for model building to obtain a color cast optimization model for the LCD screen;

[0102] Wherein, the target prediction module includes a liquid crystal screen color cast prediction data unit and a target liquid crystal screen color cast prediction data unit;

[0103] The LCD color cast prediction data unit is used to collect various LCD operating parameters of the LCD in the current cycle, obtain data corresponding to the various LCD operating parameters, and input the obtained various LCD operating parameters of the LCD into the LCD color cast optimization model to predict the LCD working condition and obtain the LCD color cast prediction data of the LCD;

[0104] A target LCD color cast prediction data unit is used to verify and optimize the LCD color cast prediction data of the LCD in the current cycle according to the historical LCD color cast prediction records, so as to obtain the target LCD color cast prediction data of the LCD in the current cycle;

[0105] Wherein, the display optimization module includes an optimization management unit;

[0106] The optimization management unit is used to obtain the target LCD color cast prediction data of the LCD screen in the current cycle, and use the LCD color cast optimization model based on the target LCD color cast prediction data to obtain the calibrated color data of the LCD screen in the current cycle, perform color superposition based on the calibrated color data, and transmit the RGB signal to the LCD screen for display. The NPU in the screen driver chip S0C uploads the target LCD color cast prediction data predicted by the LCD color cast optimization model to the cloud server, and verifies and remotely updates the model data of the LCD color cast optimization model.

[0107] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0108] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for optimizing and managing LCD screen data based on big data analysis, characterized in that: The method comprises: Step S100: obtaining historical color cast adjustment experiment records of the LCD screen, obtaining LCD screen color cast adjustment experiment data from the historical color cast adjustment experiment records, analyzing the correlation between the LCD screen operating parameters and the target LCD color cast parameters of the LCD screen, and obtaining LCD screen operating parameter related data; Step S200: based on the historical color cast adjustment experiment record of the LCD screen, an autocorrelation function diagram and a partial autocorrelation function diagram are plotted, and combined with the relevant data of the LCD screen operation parameters, the relevant order of the ARIMA model is obtained, and the model parameters of the LCD screen in the ARIMA model are estimated by the least squares method, and the LCD screen color cast optimization model is constructed according to the obtained target LCD screen performance reference data; Step S300: using the screen drive chip SOC to collect the LCD screen operating parameters of the LCD screen, and inputting the collected LCD screen operating parameters into the LCD screen color cast optimization model, predicting the working conditions of the LCD screen to obtain LCD screen color cast prediction data, obtaining historical LCD screen color cast prediction records from the cloud server, and calibrating and optimizing the LCD screen color cast prediction data based on the historical LCD screen color cast prediction records to obtain target LCD screen color cast prediction data; Step S400: Obtain the target LCD screen color cast prediction data of the LCD screen, obtain the color calibration data of the LCD screen based on the target LCD screen color cast prediction data, optimize the LCD screen color display based on the color calibration data, and upload the relevant data to the cloud server.

2. The method for optimizing and managing LCD screen data based on big data analysis according to claim 1, characterized in that: The step S100 includes: Step S101: acquiring historical color cast adjustment experiment records of the LCD screen from the cloud platform, and acquiring LCD screen color cast adjustment experiment data from the historical color cast adjustment experiment records, wherein the LCD screen color cast adjustment experiment data includes data corresponding to various LCD screen operating parameters and target LCD color cast parameters of the LCD screen; Step S102: acquiring the time points at which the cloud platform acquires the various historical color cast adjustment experiment records, and sorting the various historical color cast adjustment experiment records according to the time sequence; Step S103: analyzing the correlation between the LCD screen operating parameters and the target LCD color cast parameters of the LCD screen, wherein the specific analysis process of the correlation between the a-th LCD screen operating parameter and the target LCD color cast parameter is to obtain the value of the a-th LCD screen operating parameter in each of the historical color cast adjustment experiment records, and rank the a-th LCD screen operating parameter in each of the historical color cast adjustment experiment records according to the value, obtain the rank of the a-th LCD screen operating parameter in a certain historical color cast adjustment experiment record, and use the value of the rank as the parameter order value of the a-th LCD screen operating parameter in a certain historical color cast adjustment experiment record; Step S104: Calculate the correlation strength value U between the a-th LCD screen operating parameter and the target liquid crystal color cast parameter a : Among them, X a,i Y is represented by the parameter order value of the a-th item of LCD screen operating parameter in the i-th historical color cast adjustment experiment record; i is represented by the target liquid crystal color cast parameter, the parameter order value in the i-th historical color cast adjustment experiment record; n is the total number of the historical color cast adjustment experiment records; Step S105: when the correlation strength value between the a-th LCD screen operating parameter and the target liquid crystal color cast parameter is greater than a preset first correlation strength threshold, it is determined that there is a positive monotonic correlation between the a-th LCD screen operating parameter and the target liquid crystal color cast parameter, and the a-th LCD screen operating parameter is marked; Step S106: when the correlation strength value between the a-th LCD screen operating parameter and the target LCD color cast parameter is less than a preset second correlation strength threshold, it is determined that there is a negative monotonic correlation between the a-th LCD screen operating parameter and the target LCD color cast parameter, wherein the first correlation strength threshold is greater than the second correlation strength threshold, and the a-th LCD screen operating parameter is marked; Step S107: acquiring a plurality of LCD screen operating parameters marked in the LCD screen, and collecting the plurality of LCD screen operating parameters to obtain LCD screen operating parameter related data.

3. The method for optimizing and managing LCD screen data based on big data analysis according to claim 2, characterized in that: The step S200 includes: Step S201: Acquire various historical color cast adjustment experimental records of the LCD screen, draw an autocorrelation function graph and a partial autocorrelation function graph based on the various historical color cast adjustment experimental records, and analyze the correlation function graph and the partial autocorrelation function graph in combination with the relevant data of the LCD screen operation parameters to obtain various relevant orders of the ARIMA model of the LCD screen; Step S202: using the least squares method to estimate the model parameters of the ARIMA model to obtain the ARIMA model of the LCD screen; Step S203: Obtain target LCD performance reference data of the LCD screen from the cloud platform, perform statistical induction on the performance data of the LCD screen based on the target LCD performance reference data, and input the data into the ARIMA model of the LCD screen for model construction, so as to obtain optimization model data of the LCD screen color cast optimization model.

4. The method for optimizing and managing LCD screen data based on big data analysis according to claim 3 is characterized in that: The step S300 includes: Step S301: converting the LCD screen color cast optimization model through RKNN and running it in the NPU in the screen display driver chip SOC; Step S302: using the screen drive chip SOC, collecting various LCD screen operating parameters of the LCD screen in the current cycle, obtaining data corresponding to the various LCD screen operating parameters, and inputting the obtained various LCD screen operating parameters of the LCD screen into the LCD screen color cast optimization model, predicting the LCD screen working condition, and obtaining LCD screen color cast prediction data of the LCD screen; Step S303: acquiring each historical LCD color cast prediction record of the stored LCD screen from the cloud server, and acquiring data corresponding to a plurality of marked LCD screen operating parameters and target LCD color cast parameters in the LCD screen from the historical LCD color cast prediction records; Step S304: based on the historical LCD color cast prediction record, verify and optimize the LCD color cast prediction data of the LCD in the current cycle, and obtain the absolute value of the difference between the marked multiple items of LCD operating parameters in the historical LCD color cast prediction record and the average value of the multiple items of LCD operating parameters in the LCD in the current cycle; Step S305: when the absolute values ​​of the differences between the plurality of LCD screen operating parameters in a certain historical LCD screen color cast prediction record and the average values ​​of the plurality of LCD screen operating parameters in the LCD screen in the current cycle are all less than a preset characteristic threshold, the certain historical LCD screen color cast prediction record is recorded as a reference historical LCD screen color cast prediction record; Step S306: Obtain each comparison history LCD color cast prediction record of the LCD screen in the current cycle, and obtain the average value μ of the target LCD color cast parameter in each comparison history LCD color cast prediction record, and calculate the predicted abnormal value Y of the LCD color cast prediction data of the LCD screen in the current cycle: Wherein, X represents the average value of the target liquid crystal color cast parameter in the liquid crystal screen color cast prediction data in the current cycle; σ represents the standard deviation of the target liquid crystal color cast parameter in each of the reference historical liquid crystal screen color cast prediction records; Step S307: When the predicted abnormal value Y is greater than the preset predicted abnormal threshold, it is determined that there is a problem with the LCD screen color cast prediction data of the LCD screen in the current cycle, and the LCD screen color cast prediction data is optimized and adjusted according to the historical LCD screen color cast prediction records of the LCD screen in the current cycle to obtain target LCD screen color cast prediction data; conversely, when the predicted abnormal value Y is less than or equal to the preset predicted abnormal threshold, the LCD screen color cast prediction data is recorded as the target LCD screen color cast prediction data.

5. The method for optimizing and managing LCD screen data based on big data analysis according to claim 4, characterized in that: The step S400 includes: Step S401: acquiring target LCD color cast prediction data of the LCD in the current cycle, and obtaining color calibration data K of the LCD in the current cycle using an LCD color cast optimization model based on the target LCD color cast prediction data, wherein K=F+S, F is color uncalibrated data, and S is a module prediction supplement value of the LCD color cast optimization model; Step S402: The screen driver chip S0C in the LCD screen performs color superposition based on the color calibration data of the LCD screen in the current cycle, and transmits the RGB signal to the LCD screen for display. The NPU in the screen driver chip S0C uploads the target LCD color cast prediction data predicted by the LCD color cast optimization model to the cloud server, and verifies and remotely updates the model data of the LCD color cast optimization model.

6. A liquid crystal screen data optimization management system applied to a liquid crystal screen data optimization management method based on big data analysis as described in any one of claims 1 to 5, characterized in that: The management system includes a correlation analysis module, a model building module, a target prediction module, and a display optimization module; The correlation analysis module is used to analyze the correlation between the LCD screen operating parameters and the target LCD color cast parameters in the LCD screen color cast adjustment experimental data to obtain the LCD screen operating parameter correlation data of the target LCD color cast parameters; The model building module is used to build a color cast optimization model for a liquid crystal screen according to the acquired target liquid crystal screen performance reference data, so as to obtain a color cast optimization model for a liquid crystal screen; The target prediction module is used to predict the working condition of the LCD screen to obtain the LCD screen color cast prediction data, obtain the historical LCD screen color cast prediction records stored from the cloud server, calibrate and optimize the LCD screen color cast prediction data based on the historical LCD screen color cast prediction records, and obtain the target LCD screen color cast prediction data; The display optimization module is used to obtain the color calibration data of the LCD screen according to the target LCD screen color cast prediction data, optimize the LCD screen color display based on the color calibration data, and upload the relevant data to the cloud server.

7. The LCD screen data optimization management system according to claim 6, characterized in that: The correlation analysis module includes a correlation strength value unit and a liquid crystal screen operation parameter related data unit; The correlation strength value unit is used to calculate the correlation strength value between each LCD screen operating parameter and the target liquid crystal color cast parameter; The LCD screen operating parameter related data unit is used to obtain a plurality of LCD screen operating parameters marked in the LCD screen, and to collect the plurality of LCD screen operating parameters to obtain the LCD screen operating parameter related data of the target liquid crystal color cast parameter.

8. The LCD screen data optimization management system according to claim 6, characterized in that: The model building module includes a model building unit; The model building unit is used to obtain target LCD performance reference data of the LCD screen from the cloud platform, statistically summarize the performance data of the LCD screen according to the target LCD performance reference data, and enter the data into the ARIMA model of the LCD screen for model building to obtain the LCD screen color cast optimization model.

9. The LCD screen data optimization management system according to claim 6, characterized in that: The target prediction module includes a liquid crystal screen color cast prediction data unit and a target liquid crystal screen color cast prediction data unit; The LCD color cast prediction data unit is used to collect various LCD operating parameters of the LCD in the current cycle, obtain data corresponding to the various LCD operating parameters, and input the obtained various LCD operating parameters of the LCD into the LCD color cast optimization model to predict the LCD working condition and obtain the LCD color cast prediction data of the LCD; The target LCD color cast prediction data unit is used to verify and optimize the LCD color cast prediction data of the LCD in the current cycle according to the historical LCD color cast prediction records to obtain the target LCD color cast prediction data of the LCD in the current cycle.

10. The LCD screen data optimization management system according to claim 6, characterized in that: The display optimization module includes an optimization management unit; The optimization management unit is used to obtain target LCD color cast prediction data for the LCD screen in the current cycle, and based on the target LCD color cast prediction data, use the LCD color cast optimization model to obtain the calibrated color data of the LCD screen in the current cycle, perform color superposition based on the calibrated color data, and transmit the RGB signal to the LCD screen for display. The NPU in the screen driver chip S0C uploads the target LCD color cast prediction data predicted by the LCD color cast optimization model to the cloud server, and verifies and remotely updates the model data of the LCD color cast optimization model.

Images