OLED display screen frame number intelligent regulation and control system and method based on image analysis

Abstract

The invention discloses an OLED display screen frame number intelligent regulation and control system and method based on image analysis, and relates to the field of display screen frame number regulation and control. The method comprises the steps that the comprehensive state and definition of a picture image of a display screen with the frame number to be adjusted are obtained at equal intervals; when the definition of the picture image of the display screen with the to-be-adjusted frame number does not meet the requirement, adjusting the playing frame number of the display screen with the to-be-adjusted frame number to change the corresponding picture definition, and further enabling the definition of the picture image of the display screen at the time point to meet the requirement; after the video is played and the local definition of the video meets the requirement, the acquisition interval time of the screen image of the display screen is adjusted from the aspect of the overall definition of the played video, so that the overall definition of the played video is optimal, and the playing has better impression; by adjusting the acquisition interval time, the probability that the video picture definition in the acquisition interval time does not meet the requirement is reduced, and the overall definition of the video is improved.

Description

Technical Field

[0001] The present invention belongs to the field of display screen frame rate control, and in particular, relates to an OLED display screen frame rate intelligent control system and method based on image analysis. Background Art

[0002] A Chinese patent with announcement number CN112102780B discloses a display frame rate control method, device and computer-readable storage medium, including monitoring the current foreground program, determining the application type of the foreground program, and identifying the current functional interface of the foreground program; then determining the main content area of ​​the functional interface and identifying the display content in the main content area; determining the current display frame rate according to the application type and the content characteristics of the display content; finally, adjusting the working parameters of the display screen of the terminal device according to the display frame rate during the display period of the display content.

[0003] When using an OLED display to play videos, if the frame rate of the video does not meet the requirements of the dynamic level and complexity of the picture, the picture will appear to be noticeably stuck, especially in scenes where the picture changes quickly or objects move quickly. This stuck will be more serious and affect the viewing experience. It may also cause the movements in the picture to be incoherent, such as the body movements of the characters, the movement trajectory of the objects, etc., which will appear stiff and unnatural and unable to present a smooth dynamic effect. In the case of a high degree of picture complexity, insufficient frame rate may cause the picture to appear blurry, distorted and other problems. Summary of the invention

[0004] In view of the problems in the related art, the present invention proposes an OLED display screen frame rate intelligent control system and method based on image analysis to overcome the above-mentioned technical problems existing in the existing related art.

[0005] To solve the above technical problems, the present invention is achieved through the following technical solutions:

[0006] The present invention is an intelligent control method for the frame number of an OLED display screen based on image analysis, comprising the following steps:

[0007] S1. Set several levels of status quantities corresponding to several display screen status quantity types and combine them to obtain a comprehensive display screen status set;

[0008] S2. According to the display screen comprehensive state set, multiple historical screen images and corresponding display screen comprehensive state data are collected when the frame number display screen to be adjusted plays the video, and then the clarity data, picture comprehensive state data and corresponding playback frame number data of multiple historical screen images are collected, and a display screen comprehensive state mapping model and a display screen clarity mapping model are constructed;

[0009] S3, in conjunction with the display screen comprehensive state mapping model and the display screen picture clarity mapping model, by setting the current picture image data acquisition interval, the picture image of the display screen to be adjusted is collected and mapped out the corresponding current display screen picture comprehensive state data to be adjusted, and then the corresponding current display screen picture clarity data to be adjusted is mapped out, and finally the frame number of the video played by the display screen to be adjusted is adjusted to obtain the adjusted current display screen video;

[0010] S4, adjusting the current screen image data acquisition interval according to the adjusted current display screen video;

[0011] This solution sets several comprehensive states for the screen image of the OLED display screen, and combines the constructed display screen comprehensive state mapping model and display screen picture clarity mapping model to obtain the comprehensive state and clarity of the screen image of the display screen to be adjusted at equal intervals; when the picture image clarity of the display screen to be adjusted does not meet the requirements, the playback frame number of the display screen to be adjusted is adjusted to change the corresponding picture clarity, so that the picture image clarity of the display screen at that time point meets the requirements; since the screen image of the display screen is collected at intervals, during the interval process, if the interval time is unreasonable, during the interval time, the adjusted frame number may again fail to meet the frame number requirements of the playback scene during the interval time. Based on this, this solution adjusts the collection interval time of the screen image of the display screen from the aspect of the overall clarity of the playback video, so that the overall clarity of the playback video is optimized, so that the playback has a better viewing experience.

[0012] Preferably, the S1 comprises the following steps:

[0013] S11, set several types of state quantities related to the frame number of the OLED display screen, and obtain the display screen state quantity type set a1={a 11 ,a 12}, a 11 、a 12 Respectively represent the state quantity type of the picture dynamics and the state quantity type of the picture complexity; according to the display screen state quantity type set, several state quantity levels and corresponding state quantity value intervals corresponding to each display screen state quantity type are set to obtain a picture dynamics level set, a picture dynamics interval set, a picture complexity level set and a picture complexity interval set;

[0014] S12, combining the picture dynamic level set and the picture complexity level set to obtain several comprehensive states of the OLED display screen, and obtaining a display screen picture comprehensive state set and a corresponding picture dynamic complexity combination set a2; as follows,

[0015]

[0016] in, They respectively represent the picture dynamic degree level data and the picture complexity level data in the i-th display screen picture comprehensive state, and a′ represents the total number of display screen picture comprehensive states obtained by combination;

[0017] This solution sets the comprehensive state of the display screen from two perspectives: the degree of picture dynamics and the degree of picture complexity. These two aspects are closely related to the frame rate of the video played on the display screen; the greater the degree of picture dynamics, the higher the number of playback frames required to ensure its clarity, and the greater the degree of picture complexity, the higher the number of playback frames required to ensure its clarity.

[0018] Preferably, S2 comprises the following steps:

[0019] S21, setting an OLED display screen that needs to adjust the frame number, recorded as the display screen to be adjusted; collecting multiple historical screen images and corresponding display screen comprehensive state data when the display screen to be adjusted plays a video in coordination with the display screen comprehensive state set, the picture dynamic complexity combination set, the picture dynamic level set, the picture dynamic interval set, the picture complexity level set and the picture complexity interval set, to obtain a historical display screen image data set and a first historical display screen comprehensive state data set;

[0020] In addition, the clarity data of multiple historical screen images of the frame number to be adjusted display screen, the screen comprehensive state data and the frame number data of the corresponding frame number to be adjusted display screen when playing the video are collected to obtain a historical screen clarity data set, a second historical display screen screen comprehensive state data set and a historical video playing frame number data set;

[0021] S22, constructing a display screen comprehensive state mapping model using the historical display screen image data set and the first historical display screen comprehensive state data set;

[0022] S23, constructing a display screen picture clarity mapping model according to the historical picture clarity data set, the second historical display screen picture comprehensive state data set, and the historical video playback frame number data set;

[0023] By collecting the historical display screen image data set and the first historical display screen comprehensive state data set, data support is provided for the subsequent construction of the display screen comprehensive state mapping model; by collecting the historical picture clarity data set, the second historical display screen comprehensive state data set and the historical video playback frame number data set, data support is provided for the subsequent construction of the display screen clarity mapping model;

[0024] The display screen picture comprehensive state mapping model is used to provide a mapping tool for the subsequent real-time acquisition of the comprehensive state of the display screen, thereby facilitating the acquisition of corresponding picture clarity data through the display screen picture clarity mapping model.

[0025] Preferably, S3 comprises the following steps:

[0026] S31, setting a time interval for collecting the image data of the display screen with the frame number to be adjusted, recorded as the current image data collection interval; when the display screen with the frame number to be adjusted plays a video, collecting the image of the display screen with the frame number to be adjusted according to the current image data collection interval, and using the image of the display screen with the frame number to be adjusted collected at the current moment as the image data of the current display screen to be adjusted;

[0027] S32, obtaining the frame number data when the frame number display screen to be adjusted is playing the video in S31, and obtaining the frame number data of the video playing on the current display screen; inputting the image data of the current display screen to be adjusted into the display screen comprehensive state mapping model for mapping, and obtaining the current display screen comprehensive state data;

[0028] Setting a first screen definition threshold for the display screen to be adjusted; inputting the current screen comprehensive state data for the display screen to be adjusted and the current screen video playback frame number data into the display screen definition mapping model for mapping, and obtaining the current screen definition data for the display screen to be adjusted;

[0029] S33, when the picture clarity data of the current display screen to be adjusted is less than the picture clarity threshold of the first display screen to be adjusted, adjusting the video playback frame number data of the current display screen to obtain the current final display screen video playback frame number data; otherwise, there is no need to adjust the video playback frame number data of the current display screen;

[0030] The current final display screen video playback frame number data is used as the frame number of the video played by the display screen to be adjusted at the current moment;

[0031] S34, taking the picture image data after the next time interval of the picture image data of the current display screen to be adjusted as the picture image data of the current display screen to be adjusted, and repeating S31, S32, S33 and S34; when the picture image data of the current display screen to be adjusted is the picture image data after the last time interval, stop repeating; and obtain the adjusted current display screen video;

[0032] Since the screen image of the OLED display is constantly changing when playing video, the screen image data is obtained once at equal intervals for analysis. When the clarity does not meet the requirements, the frame rate of the video can be adjusted in time, so that when playing the segment, the frame rate of the entire video can be adjusted to a level suitable for the frame rate requirement of the video playing the segment; since the larger the frame rate of video playback, the more power is consumed when playing the video, therefore, under the premise of ensuring that the clarity when playing the segment meets the requirements, the power consumption of the entire video playback is minimized.

[0033] Preferably, S4 comprises the following steps:

[0034] S41, setting a second display screen image clarity threshold to be adjusted; measuring the overall clarity of the adjusted current display screen video to obtain overall clarity data of the current display screen video;

[0035] S42, when the overall definition data of the current display screen video is less than the second display screen picture definition threshold to be adjusted, adjusting the current screen image data acquisition interval until the overall definition data of the current display screen video is greater than or equal to the second display screen picture definition threshold to be adjusted; otherwise, there is no need to adjust the current screen image data acquisition interval;

[0036] By setting the picture clarity threshold of the second display screen to be adjusted, a quantitative basis for determining whether the overall clarity of the video meets the requirements after the clarity of each part of the video is adjusted is provided; since the scene of the video may suddenly change during the interval, such as the sudden appearance of a picture with a high degree of dynamics or a high degree of complexity, at this time, since the number of video frames is still set according to the previous picture with a lower degree of dynamics or a lower degree of complexity, the clarity of the video playback during the interval is low, which in turn affects the overall clarity of the video; therefore, by adjusting the acquisition interval, the probability of sudden changes in the video content is reduced, thereby reducing the probability of the video picture clarity not meeting the requirements during the acquisition interval, and improving the overall clarity of the video.

[0037] Preferably, adjusting the current screen image data acquisition interval in S42 includes the following steps:

[0038] S421, setting the value interval of the current screen image data acquisition interval to obtain the current acquisition interval value interval Respectively represent the lower limit and upper limit of the current screen image data acquisition interval;

[0039] Constructing a picture image acquisition interval to adjust the squirrel population; setting the maximum number of iterations of the picture image acquisition interval to adjust the squirrel population is And the current iteration number is They are recorded as the maximum number of iterations for interval adjustment and the current number of iterations for interval adjustment respectively; the dimension number of the search space of the squirrel population for the picture image acquisition interval adjustment is 1;

[0040] S422, adjusting the initial position of each squirrel in the squirrel population according to the current acquisition interval value interval setting screen image acquisition interval, and obtaining a second initial position set b 2i represents that the image acquisition interval adjusts the initial position of the i-th squirrel in the squirrel population, and b′2 represents that the image acquisition interval adjusts the size of the squirrel population; b 2i The calculation formula is as follows,

[0041]

[0042] In the formula, rand 2i Indicates that for b 2i Generate a random number between 0 and 1;

[0043] S423, construct the fitness function b′2 of the squirrel population adjusted by the picture image acquisition interval; as follows,

[0044]

[0045] In the formula, Indicates that the current screen image data collection interval is replaced by the screen image collection interval data obtained in each round of iteration, and the overall definition data of the current display screen video adjusted by executing S31, S32, S33 and S34;

[0046] S424, start iteration, and set the interval adjustment current iteration number to 1 before iteration; in the first round of iteration, use the picture image acquisition interval to adjust the fitness function b′2 of the squirrel population to calculate the fitness value of the initial position of each squirrel in the second initial position set to obtain a third fitness value set; use the maximum fitness value in the third fitness value set and the initial position of the corresponding squirrel as the third global optimal fitness and the third global optimal position respectively; update the initial position of each squirrel in the second initial position set according to the third global optimal fitness and the third global optimal position; after the update is completed, add 1 to the interval adjustment current iteration number and enter the next round of iteration;

[0047] In each other iteration process, the fitness function b′2 of the squirrel population adjusted by the picture image acquisition interval is used to calculate the fitness value of the position of each squirrel in the squirrel population adjusted by the picture image acquisition interval updated in the previous iteration process to obtain a fourth fitness value set; the maximum fitness value in the fourth fitness value set and the position of the corresponding squirrel are respectively used as the fourth global optimal fitness and the fourth global optimal position; the position of each squirrel in the squirrel population adjusted by the picture image acquisition interval updated in the previous iteration process is updated according to the fourth global optimal fitness and the fourth global optimal position; after the update is completed, the current iteration number of the interval adjustment is increased by 1 and the next iteration is entered;

[0048] S425. When a~4≥a~3, stop iteration and obtain the second final global optimal position and the second final global optimal fitness; otherwise, continue iteration until a~4≥a~3; use the second final global optimal fitness as the overall clarity data of the current display screen video after optimization; when the overall clarity data of the current display screen video after optimization is greater than or equal to the second display screen picture clarity threshold to be adjusted, the adjustment is completed; otherwise, return to S424 and continue iteration until the overall clarity data of the current display screen video after optimization is greater than or equal to the second display screen picture clarity threshold to be adjusted;

[0049] During the search process, the squirrel optimization algorithm can not only perform a global search, but also perform a detailed search in a local area, thereby improving the algorithm's ability to find the best solution. It is insensitive to the choice of initial values. Different initial values ​​may cause the algorithm to have different paths during the search process, but they will eventually converge to a better solution. During the search process, it can effectively deal with the influence of noise and outliers, thereby improving the robustness of the algorithm. It can be applied to various optimization problems, including function optimization, combinatorial optimization, parameter optimization in machine learning, etc., and has strong versatility and scalability. Based on the above advantages, this scheme uses the squirrel optimization algorithm to iteratively adjust the current screen image data acquisition interval for multiple times, and uses the overall clarity of the played video as the fitness function. Therefore, as the iteration proceeds, the overall clarity of the played video becomes higher and higher, and finally meets the requirements.

[0050] An intelligent control system for the frame number of an OLED display screen based on image analysis includes an OLED display screen state quantity level setting module, a screen comprehensive state setting module, a historical display screen data acquisition module, a mapping model building module, a frame number adjustment module for a display screen to be adjusted, and a screen image acquisition interval adjustment module;

[0051] The OLED display screen state quantity level setting module is used to set several state quantity levels corresponding to several display screen state quantity types, and obtain a picture dynamic degree level set and a picture complexity degree level set;

[0052] The picture comprehensive state setting module is used to combine the picture dynamic degree level set and the picture complexity level set to obtain the display screen picture comprehensive state set;

[0053] The historical display screen data acquisition module is used to collect multiple historical screen images when the display screen to be adjusted plays a video, the corresponding display screen comprehensive state data, the clarity data of multiple historical screen images, the comprehensive screen state data and the corresponding frame number data when the display screen to be adjusted plays a video according to the display screen comprehensive state set, the picture dynamic degree level set and the picture complexity level set, to obtain a historical display screen image data set, a first historical display screen comprehensive state data set, a historical picture clarity data set, a second historical display screen comprehensive state data set and a historical video playback frame number data set;

[0054] The mapping model construction module is used to construct a display screen comprehensive state mapping model and a display screen picture clarity mapping model according to a historical display screen image data set, a first historical display screen comprehensive state data set, a historical picture clarity data set, a second historical display screen comprehensive state data set, and a historical video playback frame number data set;

[0055] The frame number adjustment module of the display screen to be adjusted is used to cooperate with the display screen picture comprehensive state mapping model and the display screen picture clarity mapping model, collect the picture image of the display screen to be adjusted by setting the current picture image data collection interval and map the corresponding current display screen picture comprehensive state data to be adjusted, then map the corresponding current display screen picture clarity data to be adjusted according to the current display screen picture comprehensive state data, and finally adjust the frame number of the video played by the display screen to be adjusted according to the current display screen picture clarity data to be adjusted, so as to obtain the adjusted current display screen video;

[0056] The screen image acquisition interval adjustment module is used to adjust the current screen image data acquisition interval according to the adjusted current display screen video.

[0057] The present invention has the following beneficial effects:

[0058] 1. In the present invention, the comprehensive state and clarity of the picture image of the display screen whose frame number is to be adjusted are obtained at equal intervals; when the picture image clarity of the display screen whose frame number is to be adjusted does not meet the requirement, the playback frame number of the display screen whose frame number is to be adjusted is adjusted to change the corresponding picture clarity, so that the picture image clarity of the display screen at that time point meets the requirement; and after the local clarity of the video meets the requirement, the acquisition interval time of the picture image of the display screen is adjusted from the aspect of the overall clarity of the played video, so that the overall clarity of the played video is optimized, thereby making the playback have a better viewing experience.

[0059] 2. In the present invention, since the larger the number of frames of video playback is, the more power is consumed in playing the video, therefore, on the premise of ensuring that the clarity of the clip when playing meets the requirements, the local video screen is adjusted separately to minimize the power consumption of the entire video playback.

[0060] 3. The present invention reduces the probability of sudden changes in video content by adjusting the acquisition interval, thereby reducing the probability of the video picture clarity not meeting the requirements within the acquisition interval, and improving the overall video clarity.

[0061] 4. The present invention adopts the squirrel optimization algorithm to iteratively adjust the current screen image data acquisition interval for multiple times, and takes the overall clarity of the played video as the fitness function; therefore, as the iteration proceeds, the overall clarity of the played video becomes higher and higher, and finally meets the requirements.

[0062] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0064] Figure 1 It is a module schematic diagram of the intelligent control system of the frame number of an OLED display screen based on image analysis of the present invention;

[0065] Figure 2 A schematic diagram of the process of constructing a display screen comprehensive state mapping model for the present invention;

[0066] Figure 3 A schematic diagram of the process of constructing a display screen image clarity mapping model according to the present invention;

[0067] Figure 4The figure is a flow chart of the method for intelligently controlling the frame rate of an OLED display screen based on image analysis according to the present invention. DETAILED DESCRIPTION

[0068] The following will be combined with the drawings in the embodiments of the invention to clearly and completely describe the technical solutions in the embodiments of the invention. Obviously, the described embodiments are only part of the embodiments of the invention, not all of the embodiments. Based on the embodiments in the invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the invention.

[0069] Embodiment 1

[0070] See also Figure 2-4 This embodiment is an intelligent control method for the frame rate of an OLED display screen based on image analysis, comprising the following steps:

[0071] S1. Set several levels of status quantities corresponding to several display screen status quantity types and combine them to obtain a comprehensive display screen status set;

[0072] The S1 comprises the following steps:

[0073] S11, set several types of state quantities related to the frame number of the OLED display screen, and obtain the display screen state quantity type set a1={a 11 ,a 12}, a 11 、a 12 Respectively represent the state quantity type of the picture dynamics and the state quantity type of the picture complexity; according to the display screen state quantity type set, several state quantity levels and corresponding state quantity value intervals corresponding to each display screen state quantity type are set to obtain a picture dynamics level set, a picture dynamics interval set, a picture complexity level set and a picture complexity interval set;

[0074] The state quantity of the dynamic degree of the picture can be quantified by the movement speed of each object in the display screen and the speed or frequency of the object's movement direction change; the state quantity of the complexity of the picture can be quantified by the number of objects in the display screen, the richness of textures, and the number of color types; the state quantity of the dynamic degree of the picture and the state quantity of the complexity of the picture are both expressed by natural numbers, and the larger the value, the greater the dynamic degree of the picture and the complexity of the picture;

[0075] S12, combining the picture dynamic level set and the picture complexity level set to obtain several comprehensive states of the OLED display screen, and obtaining a display screen picture comprehensive state set and a corresponding picture dynamic complexity combination set a2; as follows,

[0076]

[0077] in, They respectively represent the picture dynamic degree level data and the picture complexity level data in the i-th display screen picture comprehensive state, a′ represents the total number of display screen picture comprehensive states obtained by combination; each picture comprehensive state in the display screen picture comprehensive state set is represented by a natural number;

[0078] S2. According to the display screen comprehensive state set, multiple historical screen images and corresponding display screen comprehensive state data are collected when the frame number display screen to be adjusted plays the video, and then the clarity data, picture comprehensive state data and corresponding playback frame number data of multiple historical screen images are collected, and a display screen comprehensive state mapping model and a display screen clarity mapping model are constructed;

[0079] The S2 comprises the following steps:

[0080] S21, setting an OLED display screen that needs to adjust the frame number, recorded as the display screen to be adjusted; collecting multiple historical screen images and corresponding display screen comprehensive state data when the display screen to be adjusted plays a video in coordination with the display screen comprehensive state set, the picture dynamic complexity combination set, the picture dynamic level set, the picture dynamic interval set, the picture complexity level set and the picture complexity interval set, to obtain a historical display screen image data set and a first historical display screen comprehensive state data set;

[0081] In addition, the clarity data of multiple historical screen images of the frame number to be adjusted display screen, the screen comprehensive state data and the frame number data of the corresponding frame number to be adjusted display screen when playing the video are collected to obtain a historical screen clarity data set, a second historical display screen screen comprehensive state data set and a historical video playing frame number data set;

[0082] S22, constructing a display screen comprehensive state mapping model using the historical display screen image data set and the first historical display screen comprehensive state data set;

[0083] The S22 comprises the following steps:

[0084] S221, constructing an initial CNN neural network model and setting a first training data ratio; dividing the historical display screen image data set and the first historical display screen comprehensive state data set according to the first training data ratio to obtain a historical display screen image training data set, a first historical display screen comprehensive state training data set, a historical display screen image test data set, and a first historical display screen comprehensive state test data set;

[0085] S222, setting a first training error threshold; using the first historical display screen comprehensive state training data set to annotate each image data in the historical display screen image training data set to obtain an annotated historical display screen image training data set; inputting the annotated historical display screen image training data set into the initial CNN neural network model for training; during the training process, when the training error is less than the first training error threshold, stopping the training to obtain a trained CNN neural network model; otherwise, continuing the training until the training error is less than the first training error threshold;

[0086] S223, set a first test accuracy threshold; input the historical display screen image test data set and the first historical display screen comprehensive state test data set as test data and test labels respectively into the trained CNN neural network model for testing; after the test is completed, obtain the first test accuracy data; when the first test accuracy data is greater than or equal to the first test accuracy threshold, use the trained CNN neural network model as the display screen comprehensive state mapping model; otherwise, return to S222 to continue training the trained CNN neural network model until the first test accuracy data is greater than or equal to the first test accuracy threshold;

[0087] The CNN neural network model has the following advantages in image classification: strong feature extraction capability, including automatic learning features, multi-level feature extraction, model parameter sharing and sparse connections; it also has translation invariance, that is, it is insensitive to image translation, which makes CNN robust to changes in the position and size of objects in the image; based on the above advantages, this solution constructs a display screen comprehensive state mapping model based on the CNN neural network model;

[0088] S23, constructing a display screen picture clarity mapping model according to the historical picture clarity data set, the second historical display screen picture comprehensive state data set, and the historical video playback frame number data set;

[0089] The S23 comprises the following steps:

[0090] S231, constructing an initial SVM model and setting a second training data ratio; dividing the historical picture clarity data set, the second historical display screen picture comprehensive state data set, and the historical video playback frame number data set according to the second training data ratio to obtain a historical picture clarity training data set, a second historical display screen picture comprehensive state training data set, a historical video playback frame number training data set, a historical picture clarity test data set, a second historical display screen picture comprehensive state test data set, and a historical video playback frame number test data set;

[0091] S232, setting a second training error threshold; using the second historical display screen comprehensive state training data set, the historical video playback frame number training data set as training data and the historical picture clarity training data set as training labels to input into the initial SVM model for training; during the training process, when the training error is less than the second training error threshold, stop the training to obtain a trained SVM model; otherwise, continue the training until the training error is less than the second training error threshold;

[0092] S233, setting a second test accuracy threshold; using the second historical display screen comprehensive state test data set and the historical video playback frame number test data set as test data and inputting the historical picture clarity test data set as a test label into the trained SVM model for testing; after the test is completed, obtaining the second test accuracy data; when the second test accuracy data is greater than or equal to the second test accuracy threshold, using the trained SVM model as the display screen clarity mapping model; otherwise, returning to S232 to continue training the trained SVM model until the second test accuracy data is greater than or equal to the second test accuracy threshold;

[0093] The SVM model has the following advantages in data classification: it can effectively process high-dimensional data, map data to high-dimensional space through kernel functions, and thus find the optimal classification hyperplane in high-dimensional space. Even when the data dimension is very high, it can achieve good classification results. Its decision boundary is determined by a small number of support vectors, which makes the model robust and insensitive to noise and outliers in the data. Even when there are certain noise and outliers in the data, it can maintain good classification performance. Based on the above advantages, this solution constructs a display screen clarity mapping model based on the SVM model.

[0094] S3, in conjunction with the display screen comprehensive state mapping model and the display screen picture clarity mapping model, by setting the current picture image data acquisition interval, the picture image of the display screen to be adjusted is collected and mapped out the corresponding current display screen picture comprehensive state data to be adjusted, and then the corresponding current display screen picture clarity data to be adjusted is mapped out, and finally the frame number of the video played by the display screen to be adjusted is adjusted to obtain the adjusted current display screen video;

[0095] The S3 comprises the following steps:

[0096] S31, setting a time interval for collecting the image data of the display screen with the frame number to be adjusted, recorded as the current image data collection interval; when the display screen with the frame number to be adjusted plays a video, collecting the image of the display screen with the frame number to be adjusted according to the current image data collection interval, and using the image of the display screen with the frame number to be adjusted collected at the current moment as the image data of the current display screen to be adjusted;

[0097] S32, obtaining the frame number data when the frame number display screen to be adjusted is playing the video in S31, and obtaining the frame number data of the video playing on the current display screen; inputting the image data of the current display screen to be adjusted into the display screen comprehensive state mapping model for mapping, and obtaining the current display screen comprehensive state data;

[0098] Setting a first screen definition threshold for the display screen to be adjusted; inputting the current screen comprehensive state data for the display screen to be adjusted and the current screen video playback frame number data into the display screen definition mapping model for mapping, and obtaining the current screen definition data for the display screen to be adjusted;

[0099] S33, when the picture clarity data of the current display screen to be adjusted is less than the picture clarity threshold of the first display screen to be adjusted, adjusting the video playback frame number data of the current display screen to obtain the current final display screen video playback frame number data; otherwise, there is no need to adjust the video playback frame number data of the current display screen;

[0100] The current final display screen video playback frame number data is used as the frame number of the video played by the display screen to be adjusted at the current moment;

[0101] The step of adjusting the current display screen video playback frame number data in S33 includes the following steps:

[0102] S331, setting the value interval of the current display screen video playback frame number data, and obtaining the value interval of the current display screen video playback frame number data. Respectively represent the lower limit and upper limit of the value of the frame number data of the video playback on the current display screen;

[0103] Construct a display screen video playback frame number to adjust the squirrel population; set the maximum number of iterations of the display screen video playback frame number to adjust the squirrel population And the current iteration number is They are recorded as the maximum iteration number of frame number adjustment and the current iteration number of frame number adjustment respectively; the search space dimension number of the squirrel population adjusted by the display screen video playback frame number is 1;

[0104] S332, setting the display screen video playback frame number according to the current display screen video playback frame number value interval, adjusting the initial position of each squirrel in the squirrel population, and obtaining a first initial position set , b 1i represents that the initial position of the i-th squirrel in the squirrel population is adjusted by the video playback frame number of the display screen, and b′1 represents that the scale of the squirrel population is adjusted by the video playback frame number of the display screen; b 1i The calculation formula is as follows,

[0105]

[0106] In the formula, ceil represents the rounding function; rand 1i Indicates that for b 1i Generate a random number between 0 and 1;

[0107] S333, construct the fitness function b′1 of the squirrel population by adjusting the number of frames of video playback on the display screen; as follows,

[0108]

[0109] In the formula, Indicates that the current display screen video playback frame number data obtained in each iteration and the corresponding current display screen picture comprehensive state data to be adjusted are input into the display screen picture clarity mapping model for mapping to obtain picture clarity data;

[0110] S334, start iteration, and set the current iteration number of the frame number adjustment to 1 before iteration; in the first round of iteration, use the display screen video playback frame number to adjust the fitness function b′1 of the squirrel population to calculate the fitness value of the initial position of each squirrel in the first initial position set, and obtain the first fitness value set; take the maximum fitness value in the first fitness value set and the initial position of the corresponding squirrel as the first global optimal fitness and the first global optimal position respectively; update the initial position of each squirrel in the first initial position set according to the first global optimal fitness and the first global optimal position; after the update is completed, add 1 to the current iteration number of the frame number adjustment and enter the next round of iteration;

[0111] In each other round of iteration, the fitness function b′1 of the squirrel population adjusted by the number of frames of video playback on the display screen is used to calculate the fitness value of the position of each squirrel in the squirrel population adjusted by the number of frames of video playback on the display screen obtained in the previous round of iteration, and obtain a second fitness value set; the maximum fitness value and the position of the corresponding squirrel in the second fitness value set are respectively used as the second global optimal fitness and the second global optimal position; the position of each squirrel in the squirrel population adjusted by the number of frames of video playback on the display screen obtained in the previous round of iteration is updated according to the second global optimal fitness and the second global optimal position; after the update is completed, the current iteration number of the frame adjustment is increased by 1 and the next round of iteration is entered;

[0112] S335. When a~2≥a~1, stop the iteration and obtain the first final global optimal position and the first final global optimal fitness; otherwise, continue to iterate until a~2≥a~1; use the first final global optimal fitness as the optimized picture clarity data of the current display screen to be adjusted; when the optimized picture clarity data of the current display screen to be adjusted is greater than or equal to the first picture clarity threshold of the display screen to be adjusted, the adjustment is completed, and the first final global optimal position is used as the current final display screen video playback frame number data; otherwise, return to S334 and continue to iterate until the optimized picture clarity data of the current display screen to be adjusted is greater than or equal to the first picture clarity threshold of the display screen to be adjusted;

[0113] The squirrel optimization algorithm is used to iteratively adjust the number of video frames at the current moment, and the video picture clarity data at the current moment is used as the fitness function; therefore, as the iteration proceeds, the video picture clarity at the current moment becomes higher and higher, and finally meets the clarity requirement;

[0114] S34, taking the picture image data after the next time interval of the picture image data of the current display screen to be adjusted as the picture image data of the current display screen to be adjusted, and repeating S31, S32, S33 and S34; when the picture image data of the current display screen to be adjusted is the picture image data after the last time interval, stop repeating; and obtain the adjusted current display screen video;

[0115] S4, adjusting the current screen image data acquisition interval according to the adjusted current display screen video;

[0116] The S4 comprises the following steps:

[0117] S41, setting a second display screen image clarity threshold to be adjusted; measuring the overall clarity of the adjusted current display screen video to obtain overall clarity data of the current display screen video;

[0118] S42, when the overall definition data of the current display screen video is less than the second display screen picture definition threshold to be adjusted, adjusting the current screen image data acquisition interval until the overall definition data of the current display screen video is greater than or equal to the second display screen picture definition threshold to be adjusted; otherwise, there is no need to adjust the current screen image data acquisition interval;

[0119] The step of adjusting the current screen image data acquisition interval in S42 includes the following steps:

[0120] S421, setting the value interval of the current screen image data acquisition interval to obtain the current acquisition interval value interval Respectively represent the lower limit and upper limit of the current screen image data acquisition interval;

[0121] Constructing a picture image acquisition interval to adjust the squirrel population; setting the maximum number of iterations of the picture image acquisition interval to adjust the squirrel population is And the current iteration number is They are recorded as the maximum number of iterations for interval adjustment and the current number of iterations for interval adjustment respectively; the dimension number of the search space of the squirrel population for the picture image acquisition interval adjustment is 1;

[0122] S422, adjusting the initial position of each squirrel in the squirrel population according to the current acquisition interval value interval setting screen image acquisition interval, and obtaining a second initial position set , b 2i represents that the image acquisition interval adjusts the initial position of the i-th squirrel in the squirrel population, and b′2 represents that the image acquisition interval adjusts the size of the squirrel population; b 2i The calculation formula is as follows,

[0123]

[0124] In the formula, rand 2i Indicates that for b 2i Generate a random number between 0 and 1;

[0125] S423, construct the fitness function b′2 of the squirrel population adjusted by the picture image acquisition interval; as follows,

[0126]

[0127] In the formula, Indicates that the current screen image data collection interval is replaced by the screen image collection interval data obtained in each round of iteration, and the overall definition data of the current display screen video adjusted by executing S31, S32, S33 and S34;

[0128] S424, start iteration, and set the interval adjustment current iteration number to 1 before iteration; in the first round of iteration, use the picture image acquisition interval to adjust the fitness function b′2 of the squirrel population to calculate the fitness value of the initial position of each squirrel in the second initial position set to obtain a third fitness value set; use the maximum fitness value in the third fitness value set and the initial position of the corresponding squirrel as the third global optimal fitness and the third global optimal position respectively; update the initial position of each squirrel in the second initial position set according to the third global optimal fitness and the third global optimal position; after the update is completed, add 1 to the interval adjustment current iteration number and enter the next round of iteration;

[0129] In each other iteration process, the fitness function b′2 of the squirrel population adjusted by the picture image acquisition interval is used to calculate the fitness value of the position of each squirrel in the squirrel population adjusted by the picture image acquisition interval updated in the previous iteration process to obtain a fourth fitness value set; the maximum fitness value in the fourth fitness value set and the position of the corresponding squirrel are respectively used as the fourth global optimal fitness and the fourth global optimal position; the position of each squirrel in the squirrel population adjusted by the picture image acquisition interval updated in the previous iteration process is updated according to the fourth global optimal fitness and the fourth global optimal position; after the update is completed, the current iteration number of the interval adjustment is increased by 1 and the next iteration is entered;

[0130] S425. When a~4≥a~3, stop iteration and obtain the second final global optimal position and the second final global optimal fitness; otherwise, continue iteration until a~4≥a~3; use the second final global optimal fitness as the overall clarity data of the current display screen video after optimization; when the overall clarity data of the current display screen video after optimization is greater than or equal to the second display screen picture clarity threshold to be adjusted, the adjustment is completed; otherwise, return to S424 and continue iteration until the overall clarity data of the current display screen video after optimization is greater than or equal to the second display screen picture clarity threshold to be adjusted.

[0131] Embodiment 2

[0132] See also Figure 1 This embodiment discloses an OLED display screen frame rate intelligent control system based on image analysis, which can implement the method of the above embodiment, including an OLED display screen state quantity level setting module, a picture comprehensive state setting module, a historical display screen data acquisition module, a mapping model construction module, a frame rate adjustment module for a display screen to be adjusted, and a picture image acquisition interval adjustment module;

[0133] The OLED display screen state quantity level setting module is used to set several state quantity levels corresponding to several display screen state quantity types, and obtain a picture dynamic degree level set and a picture complexity degree level set;

[0134] The picture comprehensive state setting module is used to combine the picture dynamic degree level set and the picture complexity level set to obtain the display screen picture comprehensive state set;

[0135] The historical display screen data acquisition module is used to collect multiple historical screen images when the display screen to be adjusted plays a video, the corresponding display screen comprehensive state data, the clarity data of multiple historical screen images, the comprehensive screen state data and the corresponding frame number data when the display screen to be adjusted plays a video according to the display screen comprehensive state set, the picture dynamic degree level set and the picture complexity level set, to obtain a historical display screen image data set, a first historical display screen comprehensive state data set, a historical picture clarity data set, a second historical display screen comprehensive state data set and a historical video playback frame number data set;

[0136] The mapping model construction module is used to construct a display screen comprehensive state mapping model and a display screen picture clarity mapping model according to a historical display screen image data set, a first historical display screen comprehensive state data set, a historical picture clarity data set, a second historical display screen comprehensive state data set, and a historical video playback frame number data set;

[0137] The frame number adjustment module of the display screen to be adjusted is used to cooperate with the display screen picture comprehensive state mapping model and the display screen picture clarity mapping model, collect the picture image of the display screen to be adjusted by setting the current picture image data collection interval and map the corresponding current display screen picture comprehensive state data to be adjusted, then map the corresponding current display screen picture clarity data to be adjusted according to the current display screen picture comprehensive state data, and finally adjust the frame number of the video played by the display screen to be adjusted according to the current display screen picture clarity data to be adjusted, so as to obtain the adjusted current display screen video;

[0138] The screen image acquisition interval adjustment module is used to adjust the current screen image data acquisition interval according to the adjusted current display screen video.

[0139] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0140] The preferred embodiments of the invention disclosed above are only used to help explain the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the invention, so that those skilled in the art can understand and use the invention well.

Claims

1. An intelligent control method for the frame number of an OLED display screen based on image analysis, characterized in that: The following steps are involved: S1. Set several levels of status quantities corresponding to several display screen status quantity types and combine them to obtain a comprehensive display screen status set; S2. According to the display screen comprehensive state set, multiple historical screen images and corresponding display screen comprehensive state data are collected when the frame number display screen to be adjusted plays the video, and then the clarity data, picture comprehensive state data and corresponding playback frame number data of multiple historical screen images are collected, and a display screen comprehensive state mapping model and a display screen clarity mapping model are constructed; S3, in conjunction with the display screen comprehensive state mapping model and the display screen picture clarity mapping model, by setting the current picture image data acquisition interval, the picture image of the display screen to be adjusted is collected and mapped out the corresponding current display screen picture comprehensive state data to be adjusted, and then the corresponding current display screen picture clarity data to be adjusted is mapped out, and finally the frame number of the video played by the display screen to be adjusted is adjusted to obtain the adjusted current display screen video; S4. Adjust the current screen image data acquisition interval according to the adjusted current display screen video.

2. The method for intelligently controlling the frame rate of an OLED display screen based on image analysis according to claim 1, characterized in that: The S1 comprises the following steps: S11, setting several state quantity types related to the frame number of the OLED display screen to obtain a display screen state quantity type set; setting several state quantity levels and corresponding state quantity value intervals corresponding to each display screen state quantity type according to the display screen state quantity type set to obtain a picture dynamics level set, a picture dynamics interval set, a picture complexity level set, and a picture complexity interval set; S12, combining the picture dynamic level set and the picture complexity level set to obtain several comprehensive states of the OLED display screen, and obtaining a display screen picture comprehensive state set and a corresponding picture dynamic complexity combination set.

3. The method for intelligently controlling the frame rate of an OLED display screen based on image analysis according to claim 2, characterized in that: The S2 comprises the following steps: S21, setting an OLED display screen that needs to adjust the frame number, recorded as the display screen to be adjusted; collecting multiple historical screen images and corresponding display screen comprehensive state data when the display screen to be adjusted plays a video in coordination with the display screen comprehensive state set, the picture dynamic complexity combination set, the picture dynamic level set, the picture dynamic interval set, the picture complexity level set and the picture complexity interval set, to obtain a historical display screen image data set and a first historical display screen comprehensive state data set; In addition, the clarity data of multiple historical screen images of the frame number to be adjusted display screen, the screen comprehensive state data and the frame number data of the corresponding frame number to be adjusted display screen when playing the video are collected to obtain a historical screen clarity data set, a second historical display screen screen comprehensive state data set and a historical video playing frame number data set; S22, constructing a display screen comprehensive state mapping model using the historical display screen image data set and the first historical display screen comprehensive state data set; S23, constructing a display screen picture clarity mapping model according to the historical picture clarity data set, the second historical display screen picture comprehensive state data set, and the historical video playback frame number data set.

4. The method for intelligently controlling the frame rate of an OLED display screen based on image analysis according to claim 3 is characterized in that: The display screen comprehensive state mapping model described in S22 adopts a CNN neural network model.

5. The method for intelligently controlling the frame rate of an OLED display screen based on image analysis according to claim 4 is characterized in that: The display screen picture clarity mapping model described in S23 adopts a SVM model.

6. The method for intelligently controlling the frame rate of an OLED display screen based on image analysis according to claim 5, characterized in that: The S3 comprises the following steps: S31, setting a time interval for collecting the image data of the display screen with the frame number to be adjusted, recorded as the current image data collection interval; when the display screen with the frame number to be adjusted plays a video, collecting the image of the display screen with the frame number to be adjusted according to the current image data collection interval, and using the image of the display screen with the frame number to be adjusted collected at the current moment as the image data of the current display screen to be adjusted; S32, obtaining the frame number data when the frame number display screen to be adjusted is playing the video in S31, and obtaining the frame number data of the video playing on the current display screen; inputting the image data of the current display screen to be adjusted into the display screen comprehensive state mapping model for mapping, and obtaining the current display screen comprehensive state data; Setting a first screen definition threshold for the display screen to be adjusted; inputting the current screen comprehensive state data for the display screen to be adjusted and the current screen video playback frame number data into the display screen definition mapping model for mapping, and obtaining the current screen definition data for the display screen to be adjusted; S33, when the picture clarity data of the current display screen to be adjusted is less than the picture clarity threshold of the first display screen to be adjusted, adjusting the video playback frame number data of the current display screen to obtain the current final display screen video playback frame number data; otherwise, there is no need to adjust the video playback frame number data of the current display screen; The current final display screen video playback frame number data is used as the frame number of the video played by the display screen to be adjusted at the current moment; S34, taking the picture image data after the next time interval of the picture image data of the current display screen to be adjusted as the picture image data of the current display screen to be adjusted, and repeating S31, S32, S33 and S34; when the picture image data of the current display screen to be adjusted is the picture image data after the last time interval, stop repeating; and obtain the adjusted current display screen video.

7. The method for intelligently controlling the frame rate of an OLED display screen based on image analysis according to claim 6 is characterized in that: In S33, the squirrel optimization algorithm is used to adjust the frame number data of the current display screen video playback.

8. The method for intelligently controlling the frame rate of an OLED display screen based on image analysis according to claim 7, characterized in that: The S4 comprises the following steps: S41, setting a second display screen image clarity threshold to be adjusted; measuring the overall clarity of the adjusted current display screen video to obtain overall clarity data of the current display screen video; S42. When the overall clarity data of the current display screen video is less than the second display screen picture clarity threshold to be adjusted, the current screen image data acquisition interval is adjusted until the overall clarity data of the current display screen video is greater than or equal to the second display screen picture clarity threshold to be adjusted; otherwise, there is no need to adjust the current screen image data acquisition interval.

9. The method for intelligently controlling the frame rate of an OLED display screen based on image analysis according to claim 8, characterized in that: The step of adjusting the current screen image data acquisition interval in S42 includes the following steps: S421, setting the value interval of the current screen image data acquisition interval to obtain the current acquisition interval value interval; constructing a screen image acquisition interval to adjust the squirrel population; setting the maximum number of iterations of the screen image acquisition interval to adjust the squirrel population to a-3 and the current number of iterations to a-4, which are recorded as the maximum number of iterations for interval adjustment and the current number of iterations for interval adjustment respectively; S422, adjusting the initial position of each squirrel in the squirrel population according to the current acquisition interval value interval setting screen image acquisition interval, to obtain a second initial position set; S423, constructing a fitness function for adjusting the squirrel population by using the picture image acquisition interval; S424, start iteration, and set the interval adjustment current iteration number to 1 before iteration; in each round of iteration, use the picture image acquisition interval adjustment squirrel population fitness function to calculate the fitness value of the position of each squirrel in the picture image acquisition interval adjustment squirrel population updated in the previous round of iteration, and update the position of each squirrel in the picture image acquisition interval adjustment squirrel population updated in the previous round of iteration; S425. When a~4≥a~3, stop iteration and obtain the second final global optimal position and the second final global optimal fitness; otherwise, continue iteration until a~4≥a~3; use the second final global optimal fitness as the overall clarity data of the current display screen video after optimization; when the overall clarity data of the current display screen video after optimization is greater than or equal to the second display screen picture clarity threshold to be adjusted, the adjustment is completed; otherwise, return to S424 and continue iteration until the overall clarity data of the current display screen video after optimization is greater than or equal to the second display screen picture clarity threshold to be adjusted.

10. A system for implementing the method for intelligently controlling the frame rate of an OLED display screen based on image analysis as described in any one of claims 1 to 9.

Images