Device control method and system for Mini LED display

Abstract

The present invention relates to the field of display screen control technology, and is a device control method and system for Mini LED display, comprising: using a device to be controlled, playing a training video set to obtain a playback feature vector set, calculating a video similarity set of the training video set, obtaining a fitness key value group set based on the playback feature vector set, extracting the training fitness key value group, iterating a particle swarm based on the training feature vectors and the video similarity set in the training fitness key value group to obtain an optimal brightness vector set, classifying the optimal brightness vector set based on the training video set to obtain a same-video brightness vector group set, obtaining a fitness key value group set based on the same-video brightness vector group set, and repeating the above steps until each fitness value is greater than a fitness threshold, thereby obtaining an optimal fitness key value group set. The present invention can improve the brightness control accuracy of Mini LED displays and enhance the user's viewing experience.

Description

Technical Field

[0001] The present invention relates to the field of display screen control technology, and in particular to a device control method and system for Mini LED display. Background Art

[0002] With the development of technology, Mini LED display devices have been widely used in high-end display devices such as high-end TVs, professional monitors, laptops and tablets due to their advantages such as high brightness, high contrast and excellent color performance. In order to fully tap the potential of Mini LED display devices and provide the best viewing experience, precise brightness control of the devices is particularly important.

[0003] Traditional brightness control methods for Mini LED display devices often rely on preset brightness values ​​or simple sensor feedback. Although this method can achieve brightness control to a certain extent, it is difficult to accurately respond to dynamic changes in video content in real time and cannot achieve optimal brightness adjustment in different scenarios, thus affecting the user's viewing experience. Summary of the Invention

[0004] The present invention provides a device control method and system for Mini LED display, the main purpose of which is to improve the brightness control accuracy of Mini LED display and enhance the user's viewing experience.

[0005] To achieve the above objectives, the present invention provides a device control method for Mini LED display, comprising:

[0006] receiving a display control instruction, and determining a device to be controlled based on the display control instruction, wherein the device to be controlled includes a plurality of areas to be controlled;

[0007] Using the device to be controlled, playing the pre-acquired training video set to obtain a playback feature vector set, and calculating a video similarity set of the training video set, wherein the playback feature vectors in the playback feature vector set include: a playback brightness vector and a playback color vector;

[0008] A fitness value set of the training video set is obtained using a preset questionnaire, and a key-value pairing is performed on each playback feature vector in the playback feature vector set according to the fitness value set to obtain a fitness key-value group set;

[0009] Extracting training fitness key value groups in sequence from the fitness key value group set, and determining training feature vectors in the training fitness key value groups, wherein the training feature vectors include: a brightness training vector and a color training vector;

[0010] Initializing a pre-constructed particle swarm based on the training feature vector and the video similarity set to obtain an initial particle swarm, wherein the particle swarm includes a plurality of particles;

[0011] Iterate the initial particle swarm to obtain the optimal position, determine the optimal brightness vector based on the optimal position, summarize the optimal brightness vectors, and obtain the optimal brightness vector set;

[0012] Based on the training video set, the optimal brightness vector set is classified to obtain the same-video brightness vector set. According to the same-video brightness vector set, the training video set is played to obtain the fitness adjustment key value set.

[0013] The adjusted fitness key value set is used as the fitness key value set, and the step of obtaining the fitness value set of the training video set using the preset questionnaire is returned until each fitness value in the fitness value set is greater than the preset fitness threshold, and the optimal fitness key value set is obtained, and the control of the device to be controlled is completed based on the optimal fitness key value set.

[0014] Optionally, the using the device to be controlled to play the pre-acquired training video set to obtain the playback feature vector set includes:

[0015] For each training video in the training video set, perform the following operations:

[0016] Setting a start time for playing, and at the start time, playing the training video using the multiple areas to be controlled in the device to be controlled;

[0017] According to the start time of playing, each area to be controlled is sampled in the playing step to obtain multiple playing brightness values ​​and multiple playing color values, wherein the playing brightness values ​​and the playing color values ​​correspond to the areas to be controlled one by one;

[0018] Obtaining a playback feature vector according to the plurality of playback brightness values ​​and the plurality of playback color values, wherein the playback feature vector includes: a playback brightness vector and a playback color vector;

[0019] Calculate the intermediate sampling time according to the preset sampling interval and the start time of playback;

[0020] The intermediate sampling moment is used as the start playback moment, and the process returns to the step of sampling each area to be controlled in the playback step according to the start playback moment, until the intermediate sampling moment is not less than the preset end playback moment;

[0021] The playback feature vectors are summarized to obtain a playback feature vector group, and the playback feature vector group corresponding to each training video is merged to obtain a playback feature vector set.

[0022] Optionally, calculating a video similarity set of a training video set includes:

[0023] Extracting a first training video from a training video set and constructing a video feature matrix of the first training video, wherein the video feature matrix includes color features;

[0024] Eliminate the first training video from the training video set to obtain an eliminated training video set, and sequentially extract comparison training videos from the eliminated training video set;

[0025] Constructing a comparative feature matrix of the comparative training video, and calculating video similarity based on the video feature matrix and the comparative feature matrix;

[0026] The eliminated training video set is used as the training video set, and the step of extracting the first training video in the training video set is returned to, until the eliminated training video set is an empty set;

[0027] The video similarities are aggregated to obtain a video similarity set.

[0028] Optionally, constructing a video feature matrix of the first training video includes:

[0029] According to the preset number of pictures, a single-frame picture set is extracted from the first training video;

[0030] Performing feature extraction on each single-frame image in the single-frame picture set to obtain a picture feature vector set, wherein the feature extraction includes: color feature extraction, and the picture feature vectors in the picture feature vector set correspond one-to-one to the single-frame pictures in the single-frame picture set;

[0031] Construct a video feature matrix based on the image feature vector set.

[0032] Optionally, the obtaining of the fitness value set of the training video set by using a preset questionnaire includes:

[0033] Extract the completed playback videos in the training video set in sequence;

[0034] Identify multiple video viewers based on the completed video playback, and send questionnaires to the multiple video viewers to obtain multiple viewing experience data;

[0035] Calculate the average value based on multiple viewing experience data to obtain comprehensive experience data, and calculate the fitness value based on the comprehensive experience data;

[0036] The fitness value corresponding to each completed video is summarized to obtain a fitness value set.

[0037] Optionally, the pre-constructed particle swarm is initialized based on the training feature vector and the video similarity set to obtain an initial particle swarm, including:

[0038] Eliminate the training fitness key value group from the fitness key value group set to obtain a comparison fitness key value group set;

[0039] Extracting contrast fitness key value groups in sequence from the contrast fitness key value group set, and determining contrast parameter groups in the contrast fitness key value groups, wherein the contrast parameter groups include: a brightness contrast vector, a color contrast vector, and a contrast fitness value;

[0040] Extracting particles in sequence from the particle group to generate initial velocities of the particles;

[0041] generating an initial query vector based on a brightness training vector in the training feature vector, and recording the initial query vector as an initial position;

[0042] According to the initial query vector, determine the fitness value weight and comparison similarity of the comparison fitness key value group;

[0043] Summarizing the fitness value weight, comparative similarity, and comparative fitness value of each comparative fitness key value group in the comparative fitness key value group set to obtain a fitness value weight set, a comparative similarity set, and a comparative fitness value set;

[0044] Calculate the initial fitness value according to the fitness value weight set, the comparison similarity set and the comparison fitness value set;

[0045] Based on the initial fitness value, the initial position and the initial velocity, initial particles are generated, and the initial particles are aggregated to obtain an initial particle group.

[0046] Optionally, determining the fitness value weight and the comparison similarity of the fitness key value group according to the initial query vector includes:

[0047] Calculate the fitness value weight according to the brightness contrast vector, the initial query vector, the color training vector and the color contrast vector;

[0048] The main training video and the comparative training video corresponding to the training fitness key group and the comparative fitness key group are respectively determined, and the comparative similarity between the main training video and the comparative training video is identified in a video similarity set.

[0049] Optionally, calculating the fitness value weight according to the brightness contrast vector, the initial query vector, the color training vector, and the color contrast vector includes:

[0050] The fitness value weight is calculated using the following formula:

[0051]

[0052] in, represents the fitness value weight, represents the activation function, represents the brightness contrast vector, represents the initial query vector, The vector dimension representing the brightness contrast vector, represents the color contrast vector, represents the color training vector, The dimension of the vector representing the color contrast vector.

[0053] Optionally, the calculating the initial fitness value includes:

[0054] According to the fitness value weight set, the comparison similarity set and the comparison fitness value set, the initial fitness value is calculated using the following formula:

[0055]

[0056] in, represents the initial fitness value, Indicates the number of contrast similarities in the contrast similarity set, Indicates the first Comparative similarity, Indicates the first Fitness value weights, Indicates the first Comparative fitness values.

[0057] To achieve the above objectives, the present invention further provides a device control system for Mini LED display, comprising:

[0058] a playback vector extraction module, configured to receive a display control instruction, determine a device to be controlled based on the display control instruction, wherein the device to be controlled includes multiple areas to be controlled, use the device to be controlled to play a pre-acquired training video set to obtain a playback feature vector set, and calculate a video similarity set for the training video set, wherein the playback feature vectors in the playback feature vector set each include: a playback brightness vector and a playback color vector;

[0059] A fitness survey module is used to obtain a fitness value set of a training video set using a preset questionnaire, perform key-value pairing on each playback feature vector in the playback feature vector set based on the fitness value set to obtain a fitness key value group set, sequentially extract training fitness key value groups from the fitness key value group set, and determine training feature vectors in the training fitness key value groups, wherein the training feature vectors include: a brightness training vector and a color training vector;

[0060] An optimal brightness determination module is used to initialize a pre-constructed particle swarm based on the training feature vector and the video similarity set to obtain an initial particle swarm, wherein the particle swarm includes multiple particles, iterate the initial particle swarm to obtain an optimal position, and determine an optimal brightness vector based on the optimal position, and summarize the optimal brightness vectors to obtain an optimal brightness vector set;

[0061] The video playback return module is used to classify the optimal brightness vector set based on the training video set to obtain the same-video brightness vector group set, play the training video set according to the same-video brightness vector group set, obtain the adjustment fitness key value group set, use the adjustment fitness key value group set as the fitness key value group set, and return to the step of obtaining the fitness value set of the training video set using a preset questionnaire until each fitness value in the fitness value set is greater than the preset fitness threshold, and the optimal fitness key value group set is obtained.

[0062] In order to solve the above problem, the present invention further provides an electronic device, comprising:

[0063] a memory storing at least one instruction; and

[0064] The processor executes the instructions stored in the memory to implement the device control method for Mini LED display described above.

[0065] In order to solve the above problems, the present invention also provides a computer-readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned device control method for Mini LED display.

[0066] In order to solve the problems described in the background technology, the present invention first plays a training video set and obtains a playback feature vector set and a video similarity set, which provides feature data support based on the actual playback scene for subsequent brightness optimization, helps to more accurately analyze the performance of different video contents under different brightness conditions, and provides a data basis for brightness optimization. Then, the user's subjective viewing experience is collected through a questionnaire, quantified as a fitness value, and the fitness value is associated with the playback feature vector, which can combine the user's subjective feelings with the objective brightness and color features, and provide a user perception-level feedback basis for the subsequent optimization algorithm, so that the brightness optimization is more in line with the user's actual viewing needs. Furthermore, the particle swarm is initialized based on the training feature vector and the video similarity set to obtain the initial particle swarm. By combining the training feature vector and the video similarity set, the particle swarm is initialized to obtain the initial particle swarm. Initializing the particle swarm with a similarity set can make the distribution of the initial particle swarm more targeted and reasonable, helping to improve the efficiency and effectiveness of the particle swarm optimization algorithm. The initial particle swarm is then iterated to obtain the optimal position, and based on the optimal position, the optimal brightness vector is determined. The optimal brightness vectors are summarized to obtain the optimal brightness vector set. This step, through the iterative optimization process, can continuously adjust the brightness control strategy and gradually approach the optimal brightness vector, thereby achieving brightness optimization based on the user's viewing experience. Finally, by using the adjusted fitness key value set as the fitness key value set, a cyclic iterative optimization is completed, and the optimal fitness key value set is obtained. This step, through cyclic iterative optimization, can continuously adjust and improve the brightness control strategy until the fitness threshold is reached, thereby ensuring that the final brightness control solution can meet the user's viewing experience requirements. Therefore, the present invention can improve the brightness control accuracy of Mini LED displays and enhance the user's viewing experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 A schematic flow chart of a device control method for Mini LED display provided by one embodiment of the present invention;

[0068] Figure 2 This is a functional module diagram of a device control system for Mini LED display provided by one embodiment of the present invention;

[0069] Figure 3 A schematic structural diagram of an electronic device for implementing the device control method for Mini LED display provided in one embodiment of the present invention.

[0070] Description of reference numerals:

[0071] 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0072] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0073] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0074] The embodiments of the present application provide a device control method for a Mini LED display. The execution subject of the device control method for a Mini LED display includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiments of the present application. In other words, the device control method for a Mini LED display can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0075] Reference Figure 1 FIG2 is a flow chart of a device control method for a Mini LED display according to an embodiment of the present invention. In this embodiment, the device control method for a Mini LED display includes:

[0076] S1. Receive a display control instruction, and determine a device to be controlled based on the display control instruction, wherein the device to be controlled includes multiple areas to be controlled.

[0077] It is understood that the display control instruction refers to a manually initiated instruction to control a specific display device. The device to be controlled refers to the specific display device indicated by the display control instruction. The device to be controlled is a Mini LED display device, and the device to be controlled is composed of multiple screens. The area to be controlled refers to the screen in the device to be controlled.

[0078] S2. Using the device to be controlled, play the pre-acquired training video set to obtain a playback feature vector set, and calculate a video similarity set of the training video set, wherein the playback feature vectors in the playback feature vector set include: a playback brightness vector and a playback color vector.

[0079] It can be understood that the training video set refers to a collection of videos used to train the device to be controlled. The training video set includes multiple training videos, and in order to ensure the comprehensiveness of the training, each training video is of different types, for example: natural scenery videos, including scenes such as mountains, forests, lakes, etc., tunnel or night scene videos in low-light environments, fast-motion scene videos, such as sports events or racing scenes, etc.

[0080] Furthermore, when the training video is played using the device to be controlled, the backlight brightness of the device to be controlled is changed at different playback times, so that the training video has different visual perceptions, and the brightness corresponding to the best visual perception is used as the actual brightness for comparison in actual control, wherein the visual perception corresponds to the subsequent fitness value.

[0081] It is understood that the playback feature vector refers to a vector representing the visual appearance of a training video during playback. This vector represents the characteristics of the training video from multiple dimensions, including brightness and color, where the brightness and color dimensions correspond to the playback brightness vector and color vector, respectively. The video similarity set includes multiple video similarities, and video similarity refers to the similarity between two different training videos in the training video set. This similarity is the similarity in visual appearance of the training videos, not the similarity in content.

[0082] In detail, the method of using the device to be controlled to play the pre-acquired training video set to obtain the playback feature vector set includes:

[0083] For each training video in the training video set, perform the following operations:

[0084] Setting a start time for playing, and at the start time, playing the training video using the multiple areas to be controlled in the device to be controlled;

[0085] According to the start time of playing, each area to be controlled is sampled in the playing step to obtain multiple playing brightness values ​​and multiple playing color values, wherein the playing brightness values ​​and the playing color values ​​correspond to the areas to be controlled one by one;

[0086] Obtaining a playback feature vector according to the plurality of playback brightness values ​​and the plurality of playback color values, wherein the playback feature vector includes: a playback brightness vector and a playback color vector;

[0087] Calculate the intermediate sampling time according to the preset sampling interval and the start time of playback;

[0088] The intermediate sampling moment is used as the start playback moment, and the process returns to the step of sampling each area to be controlled in the playback step according to the start playback moment, until the intermediate sampling moment is not less than the preset end playback moment;

[0089] The playback feature vectors are summarized to obtain a playback feature vector group, and the playback feature vector group corresponding to each training video is merged to obtain a playback feature vector set.

[0090] It should be noted that the start time of playback refers to the time when the training video begins playing. Sampling refers to the use of a brightness sensor and a color sensor to detect the brightness and color in each area to be controlled. The playback brightness value is the brightness value (in nits) within the area to be controlled. The playback color value refers to the average color value of each lamp bead within the area to be controlled. The color value is the weighted average of the color channel values ​​of the corresponding lamp bead.

[0091] Furthermore, the playback feature vector obtained according to the multiple playback brightness values ​​and the multiple playback color values ​​is: the playback feature vector is ,in, Indicates the playback brightness value. Represents the playback color value. The sampling interval refers to a constant set manually. The intermediate sampling time is expressed as: ,in, represents the intermediate sampling time, Indicates the time to start playing. Represents the sampling interval. The playback feature vector groups corresponding to each training video are merged to obtain the following playback feature vector set: the playback feature vector group corresponding to training video A is (vector A1, vector A2), and the playback feature vector group corresponding to training video B is (vector B1, vector B2). Then, after merging the playback feature vector groups corresponding to training videos A and B, the playback feature vector set obtained is (vector A1, vector A2, vector B1, vector B2).

[0092] In detail, the calculation of the video similarity set of the training video set includes:

[0093] Extracting a first training video from a training video set and constructing a video feature matrix of the first training video, wherein the video feature matrix includes color features;

[0094] Eliminate the first training video from the training video set to obtain an eliminated training video set, and sequentially extract comparison training videos from the eliminated training video set;

[0095] Constructing a comparative feature matrix of the comparative training video, and calculating video similarity based on the video feature matrix and the comparative feature matrix;

[0096] The eliminated training video set is used as the training video set, and the step of extracting the first training video in the training video set is returned to, until the eliminated training video set is an empty set;

[0097] The video similarities are aggregated to obtain a video similarity set.

[0098] It should be explained that the first training video refers to the training video ranked first in the training video set. The video feature matrix refers to a matrix representing the video features of the first training video, which includes brightness features and color features. The eliminated training video set refers to the training video set after the first training video is eliminated. The comparative training video refers to the eliminated training video in the eliminated training video set. Since the comparative training video is used for subsequent comparison with the first training video, it is named the comparative training video. The comparative feature matrix refers to a matrix representing the video features of the comparative training video.

[0099] In detail, the video feature matrix of the first training video is constructed, including:

[0100] According to the preset number of pictures, a single-frame picture set is extracted from the first training video;

[0101] Performing feature extraction on each single-frame image in the single-frame picture set to obtain a picture feature vector set, wherein the feature extraction includes: color feature extraction, and the picture feature vectors in the picture feature vector set correspond one-to-one to the single-frame pictures in the single-frame picture set;

[0102] Construct a video feature matrix based on the image feature vector set.

[0103] It is understood that the number of images refers to a manually set constant, which represents the number of single-frame images in a single-frame image set. The single-frame image set refers to a collection of images of each frame number in the first training video. For example, if a first training video has a total of 90 seconds and the number of images is set to 10, then a picture is extracted from the first training video every 9 seconds to obtain a single-frame image set. The image feature vector refers to a vector representing the color features in a single-frame image, wherein the color feature extraction is as follows: converting the single-frame image from the RGB color space to the HSV color space, which contains three channels: a separated hue channel (H), a saturation channel (S), and a value channel (V), performing block processing on each channel in each HSV color space, dividing the image into several sub-regions, and calculating the color histogram of each sub-region, wherein the separated hue channel uses 36 bins, and the saturation and value channels use 8 bins each, and the histogram features of each sub-region are sequentially spliced ​​to form a multi-dimensional color feature vector.

[0104] It should be explained that the video feature matrix is ​​expressed as:

[0105]

[0106] in, represents the video feature matrix, Represents the first picture feature vector in the picture feature vector set, The vector dimension representing the image feature vector, and Respectively represent the first vector element and the first vector element in the first picture feature vector vector elements, Represents the first image feature vectors, Represents the number of picture feature vectors in the picture feature vector set, and Respectively represent The first vector element and the vector elements.

[0107] S3. Obtain a fitness value set of the training video set using a preset questionnaire, and perform key-value pairing on each playback feature vector in the playback feature vector set based on the fitness value set to obtain a fitness key-value group set.

[0108] It can be understood that the questionnaire refers to a questionnaire containing multiple questions. In order to quantify the impact of different brightness control strategies (the brightness value of each area to be controlled in the device to be controlled) on the viewer's viewing experience, a plurality of questions with numerical options are set in the questionnaire. These include multiple aspects, for example: since different brightness strategies will present different clarity under different video content, such as under the same brightness performance, when the video screen is a tunnel, the viewer's viewing clarity is lower, and when the video screen is a blue sky, the viewer's viewing clarity is higher, so it is necessary to set a viewing clarity question. Similarly, different brightness will also affect the viewer's eye comfort, and eye comfort questions can also be set.

[0109] For example, the questionnaire is as follows: Question 1: How do you think the details of the current image are? A: Very clear, B: Relatively clear, C: Average, D: Unclear; Question 2: Do you think the current brightness is glaring? A: Very soft, B: Relatively soft, C: Slightly glaring, D: Very glaring. A, B, C, and D are assigned values ​​of 1, 2, 3, and 4, respectively.

[0110] It is clear that the fitness value refers to the numerical value that quantifies the visual perception of the training video during playback. The higher the fitness value, the better the visual perception. Since visual perception is affected by screen brightness during playback, and different screen colors will also produce different visual perceptions under the same brightness, it is necessary to introduce a subsequent particle swarm optimization algorithm to find a brightness adjustment strategy that can achieve the best visual perception under the same color conditions. Therefore, in the subsequent particle swarm optimization algorithm, the position of the particle represents the multiple playback brightness of multiple areas to be controlled, and the fitness value of the particle is the fitness value at this location.

[0111] Furthermore, each playback feature vector corresponds to a training video, and then the fitness value corresponding to the training video is identified, and the playback feature vector and the fitness value are key-paired to obtain a fitness key-value group, which is expressed as (U:P), where U represents the playback feature vector and P represents the fitness value.

[0112] In detail, the method of obtaining the fitness value set of the training video set using a preset questionnaire includes:

[0113] Extract the completed playback videos in the training video set in sequence;

[0114] Identify multiple video viewers based on the completed video playback, and send questionnaires to the multiple video viewers to obtain multiple viewing experience data;

[0115] Calculate the average value based on multiple viewing experience data to obtain comprehensive experience data, and calculate the fitness value based on the comprehensive experience data;

[0116] The fitness value corresponding to each completed video is summarized to obtain a fitness value set.

[0117] It should be noted that the "completed video" refers to a training video that has completed playback in the training video set. The "video viewer" refers to the experimenter who has completed the video. The viewing experience data refers to the data obtained after completing the questionnaire. Each viewing experience data corresponds to a video viewer. The viewing experience data is obtained as follows: after a video viewer completes the questionnaire, the options corresponding to each question in the completed questionnaire are A, A, B, and D, respectively, where the corresponding values ​​for these options are 1, 1, 2, and 4, respectively. The viewing experience data is then represented as (1, 1, 2, 4). The comprehensive experience data refers to experience data obtained after mean calculation. The mean calculation based on multiple viewing experience data is as follows: the multiple viewing experience data are (1, 1, 2, 4), (1, 2, 2, 4), and (2, 2, 3, 3). The mean calculations for these viewing experience data are: (1+1+2) / 3=1.3, (1+2+2) / 3=1.7, (2+2+3) / 3=2.3, (4+4+3) / 3=3.7, resulting in the comprehensive experience data being (1.3, 1.7, 2.3, 3.7). Calculating the fitness value based on the comprehensive experience data is as follows: adding each data point in the comprehensive experience data to obtain the fitness value.

[0118] S4. Extract training fitness key value groups in sequence from the fitness key value group set, and determine training feature vectors in the training fitness key value groups, wherein the training feature vectors include: brightness training vectors and color training vectors.

[0119] It is clear that the training fitness key group refers to the fitness key group in the fitness key group set. The training feature vector refers to the playback feature vector in the training fitness key group, and the brightness training vector and color training vector respectively represent the playback brightness vector and playback color vector in the training feature vector.

[0120] S5. Initialize the pre-constructed particle swarm based on the training feature vector and the video similarity set to obtain an initial particle swarm, wherein the particle swarm includes a plurality of particles.

[0121] It is understood that the particle swarm refers to the set of candidate solutions used to search for the optimal solution in the particle swarm optimization (PSO) algorithm. Each particle represents a possible brightness control strategy (i.e., a brightness combination of multiple areas to be controlled), and its position and velocity are dynamically adjusted during the iteration process to approach the optimal solution. The initial particle swarm refers to the initialized particle swarm.

[0122] In detail, the pre-constructed particle swarm is initialized based on the training feature vector and the video similarity set to obtain the initial particle swarm, including:

[0123] Eliminate the training fitness key value group from the fitness key value group set to obtain a comparison fitness key value group set;

[0124] Extracting contrast fitness key value groups in sequence from the contrast fitness key value group set, and determining contrast parameter groups in the contrast fitness key value groups, wherein the contrast parameter groups include: a brightness contrast vector, a color contrast vector, and a contrast fitness value;

[0125] Extracting particles in sequence from the particle group to generate initial velocities of the particles;

[0126] generating an initial query vector based on a brightness training vector in the training feature vector, and recording the initial query vector as an initial position;

[0127] According to the initial query vector, determine the fitness value weight and comparison similarity of the comparison fitness key value group;

[0128] Summarizing the fitness value weight, comparative similarity, and comparative fitness value of each comparative fitness key value group in the comparative fitness key value group set to obtain a fitness value weight set, a comparative similarity set, and a comparative fitness value set;

[0129] Calculate the initial fitness value according to the fitness value weight set, the comparison similarity set and the comparison fitness value set;

[0130] Based on the initial fitness value, the initial position and the initial velocity, initial particles are generated, and the initial particles are aggregated to obtain an initial particle group.

[0131] It should be explained that the contrast fitness key value group set refers to the fitness key value group set after the training fitness key value group is eliminated. The contrast parameter group refers to a combination of brightness contrast vector, color contrast vector and contrast fitness value, wherein the brightness contrast vector and color contrast vector refer to the playback brightness vector and playback color vector contained in the playback feature vector in the contrast fitness key value group. The contrast fitness value refers to the fitness value in the contrast fitness key value group. The initial query vector refers to the vector obtained after performing a random function change on the basis of the brightness training vector, and the random function change refers to superimposing Gaussian noise on each dimension of the brightness training vector, wherein the Gaussian noise is expressed as: ,in, Indicates the preset noise intensity coefficient, which is set manually. The mean is 0 and the variance is The fitness weight refers to the similarity between the keys in the contrast fitness key group (brightness contrast vector and color contrast vector) and the initial query vector and color training vector. The contrast similarity refers to the video similarity between the training video corresponding to the contrast fitness key group and the training video corresponding to the training fitness key group. The initial velocity refers to the initial movement direction and speed of the particle in the solution space, and is generated randomly within a preset velocity range.

[0132] Furthermore, since it is impossible to obtain the fitness value of each particle in each iterative update through a questionnaire in real-time particle swarm iteration, an attention mechanism is introduced here, in which all fitness values ​​in the contrast fitness key-value group set are used as values, and all brightness contrast vectors and color contrast vectors in the contrast fitness key-value group set are used as keys. The attention weight of each value is obtained through the initial query vector, color training vector, brightness contrast vector and color contrast vector. Considering the influence of different training videos on the fitness value, contrast similarity is introduced in the attention weight. The fitness value of the particle can be obtained through the corresponding attention weight and the corresponding value (contrast fitness) of each contrast fitness key-value group (the acquisition method can refer to the calculation method of the initial fitness).

[0133] It can be understood that generating an initial particle based on the initial fitness value, the initial position and the initial velocity means that the particle position, the particle velocity and the particle fitness value of the initial particle are the initial position, the initial velocity and the initial fitness value respectively.

[0134] In detail, the determination of the fitness value weight and the comparison similarity of the fitness key value group based on the initial query vector includes:

[0135] Calculate the fitness value weight according to the brightness contrast vector, the initial query vector, the color training vector and the color contrast vector;

[0136] The main training video and the comparative training video corresponding to the training fitness key group and the comparative fitness key group are respectively determined, and the comparative similarity between the main training video and the comparative training video is identified in a video similarity set.

[0137] It can be understood that the main training video and the comparative training video refer to the training videos corresponding to the training fitness key value group and the comparative fitness key value group respectively.

[0138] Specifically, the calculation of the fitness value weight according to the brightness contrast vector, the initial query vector, the color training vector, and the color contrast vector includes:

[0139] The fitness value weight is calculated using the following formula:

[0140]

[0141] in, represents the fitness value weight, represents the activation function, represents the brightness contrast vector, represents the initial query vector, The vector dimension representing the brightness contrast vector, represents the color contrast vector, represents the color training vector, The dimension of the vector representing the color contrast vector.

[0142] In detail, the calculation of the initial fitness value includes:

[0143] According to the fitness value weight set, the comparison similarity set and the comparison fitness value set, the initial fitness value is calculated using the following formula:

[0144]

[0145] in, represents the initial fitness value, Indicates the number of contrast similarities in the contrast similarity set, Indicates the first Comparative similarity, Indicates the first Fitness value weights, Indicates the first Comparative fitness values.

[0146] S6. Iterate the initial particle swarm to obtain the optimal position, determine the optimal brightness vector based on the optimal position, summarize the optimal brightness vectors, and obtain the optimal brightness vector set.

[0147] It is understood that the optimal position refers to the position corresponding to the particle with the highest fitness value during the particle swarm optimization iteration process, and the brightness vector corresponding to this position can maximize the viewer's visual experience (i.e., the fitness value is the highest). The optimal brightness vector refers to the vector corresponding to the optimal position.

[0148] Furthermore, the optimal position is represented as an optimal brightness vector, which includes multiple optimal brightnesses. The multiple optimal brightnesses represent the optimal brightness adjustment strategies of the corresponding training video at different times.

[0149] S7. Based on the training video set, the optimal brightness vector set is classified to obtain a same-video brightness vector set. Based on the same-video brightness vector set, the training video set is played to obtain an adjustment fitness key value set.

[0150] It is clear that since the optimal brightness vector set contains the optimal brightness vectors of all training videos (according to the content of S2 of this embodiment, a playback brightness vector corresponds to a start time of a training video, so the optimal brightness vector also corresponds to a start time of a training video), it is necessary to classify the optimal brightness vectors according to the training video set. Multiple optimal brightness vectors corresponding to the same training video are recorded as a same-video brightness vector group. When playing the training video, the corresponding same-video brightness vector group will be used to control the brightness of the training video playback process. The adjustment fitness key value group set refers to the fitness key value group set obtained after playing according to the same-video brightness vector group set.

[0151] For example, a same-video brightness vector group is: at moment A, the same-video brightness vector is (600nits, 650nits, 700nits), where 600nits, 650nits and 700nits respectively represent the brightness of multiple areas to be controlled in the device to be controlled at moment A; at moment B, the same-video brightness vector is (600nits, 600nits, 700nits). When playing the training video corresponding to the same-video brightness vector group, the brightness will be adjusted according to the brightness corresponding to the moment.

[0152] S8. Use the adjusted fitness key value set as the fitness key value set, and return to the step of obtaining the fitness value set of the training video set using the preset questionnaire, until each fitness value in the fitness value set is greater than the preset fitness threshold, and obtain the optimal fitness key value set, and complete the control of the device to be controlled based on the optimal fitness key value set.

[0153] It is clear that the fitness threshold refers to an artificially set constant. When the fitness value is greater than the fitness threshold, it means that the brightness control strategy at this time can bring a better viewing experience.

[0154] Furthermore, the optimal fitness key set refers to the fitness key set obtained in the last return step. During the actual playback process, the video played will not be the training video set, but will be recorded as the actual playback video. In order to ensure the visual perception of the actual playback video at different times, the optimal fitness key set is used to perform the following operations: at a certain sampling time, the actual color vector of the actual playback video is obtained, and the optimal brightness vector at the next time is obtained through particle swarm optimization, wherein the optimal fitness key set is used to generate the fitness value of each particle in the particle swarm. The method of generating this fitness value is the same as the above-mentioned step of calculating the initial fitness value based on the fitness value weight set, the comparative similarity set, and the comparative fitness value set, wherein the optimal fitness key set corresponds to the comparative fitness key set.

[0155] In order to solve the problems described in the background technology, the present invention first plays a training video set and obtains a playback feature vector set and a video similarity set, which provides feature data support based on the actual playback scene for subsequent brightness optimization, helps to more accurately analyze the performance of different video contents under different brightness conditions, and provides a data basis for brightness optimization. Then, the user's subjective viewing experience is collected through a questionnaire, quantified as a fitness value, and the fitness value is associated with the playback feature vector, which can combine the user's subjective feelings with the objective brightness and color features, and provide a user perception-level feedback basis for the subsequent optimization algorithm, so that the brightness optimization is more in line with the user's actual viewing needs. Furthermore, the particle swarm is initialized based on the training feature vector and the video similarity set to obtain the initial particle swarm. By combining the training feature vector and the video similarity set, the particle swarm is initialized to obtain the initial particle swarm. Initializing the particle swarm with a similarity set can make the distribution of the initial particle swarm more targeted and reasonable, helping to improve the efficiency and effectiveness of the particle swarm optimization algorithm. The initial particle swarm is then iterated to obtain the optimal position, and based on the optimal position, the optimal brightness vector is determined. The optimal brightness vectors are summarized to obtain the optimal brightness vector set. This step, through the iterative optimization process, can continuously adjust the brightness control strategy and gradually approach the optimal brightness vector, thereby achieving brightness optimization based on the user's viewing experience. Finally, by using the adjusted fitness key value set as the fitness key value set, a cyclic iterative optimization is completed, and the optimal fitness key value set is obtained. This step, through cyclic iterative optimization, can continuously adjust and improve the brightness control strategy until the fitness threshold is reached, thereby ensuring that the final brightness control solution can meet the user's viewing experience requirements. Therefore, the present invention can improve the brightness control accuracy of Mini LED displays and enhance the user's viewing experience.

[0156] like Figure 2 , which is a functional module diagram of a device control system for Mini LED display provided by one embodiment of the present invention.

[0157] The device control system 100 for Mini LED displays described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the device control system 100 for Mini LED displays can include a playback vector extraction module 101, a fitness survey module 102, an optimal brightness determination module 103, and a video playback return module 104. A module, also referred to as a unit, is a series of computer program segments that can be executed by an electronic device processor and perform a fixed function, and is stored in the electronic device's memory.

[0158] The playback vector extraction module 101 is configured to receive a display control instruction, determine a device to be controlled based on the display control instruction, wherein the device to be controlled includes multiple areas to be controlled, use the device to be controlled to play a pre-acquired training video set to obtain a playback feature vector set, and calculate a video similarity set of the training video set, wherein the playback feature vectors in the playback feature vector set each include: a playback brightness vector and a playback color vector;

[0159] The fitness survey module 102 is configured to obtain a fitness value set of the training video set using a preset questionnaire, perform key-value pairing on each playback feature vector in the playback feature vector set based on the fitness value set to obtain a fitness key value group set, sequentially extract training fitness key value groups from the fitness key value group set, and determine training feature vectors in the training fitness key value groups, wherein the training feature vectors include: a brightness training vector and a color training vector;

[0160] The optimal brightness determination module 103 is used to initialize a pre-constructed particle swarm based on the training feature vector and the video similarity set to obtain an initial particle swarm, wherein the particle swarm includes multiple particles, iterate the initial particle swarm to obtain an optimal position, and determine an optimal brightness vector based on the optimal position, and summarize the optimal brightness vectors to obtain an optimal brightness vector set;

[0161] The video playback return module 104 is used to classify the optimal brightness vector set based on the training video set to obtain the same-video brightness vector group set, play the training video set based on the same-video brightness vector group set to obtain the adjustment fitness key value group set, use the adjustment fitness key value group set as the fitness key value group set, and return to the step of obtaining the fitness value set of the training video set using the preset questionnaire until each fitness value in the fitness value set is greater than the preset fitness threshold, and the optimal fitness key value group set is obtained.

[0162] In detail, the modules in the device control system 100 for Mini LED display in the embodiment of the present invention are used in the same manner as above. Figure 1The same technical means are used as the device control method for Mini LED display described in , and can produce the same technical effects, so they will not be repeated here.

[0163] like Figure 3 , which is a structural diagram of an electronic device for implementing a device control method for Mini LED display provided by an embodiment of the present invention.

[0164] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a device control method program for Mini LED display.

[0165] The memory 11 includes at least one type of readable storage medium, including flash memory, a mobile hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 1. Furthermore, the memory 11 includes both an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can be used not only to store application software installed in the electronic device 1 and various types of data, such as the code of the device control method program for the Mini LED display, but also to temporarily store data that has been output or is about to be output.

[0166] In some embodiments, the processor 10 may be composed of an integrated circuit, such as a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 10 is the control core (Control Unit) of the electronic device, connecting the various components of the entire electronic device using various interfaces and circuits. It executes or executes programs or modules stored in the memory 11 (such as a device control method program for a Mini LED display) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0167] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to enable communication between the memory 11 and at least one processor 10, etc.

[0168] Figure 3 Only the electronic device with components is shown, and it can be understood by those skilled in the art that Figure 3 The structure shown does not constitute a limitation on the electronic device 1 , and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0169] For example, although not shown, the electronic device 1 may further include a power source (e.g., a battery) to power various components. Preferably, the power source may be logically connected to the at least one processor 10 via a power management system, thereby enabling functions such as charge management, discharge management, and power consumption management through the power management system. The power source may further include any components such as one or more DC or AC power sources, a recharging system, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not further described here.

[0170] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0171] Optionally, the electronic device 1 may further include a user interface, which may be a display or an input unit (such as a keyboard). Optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. The display may also be appropriately referred to as a display screen or a display unit, and is used to display information processed by the electronic device 1 and to display a visual user interface.

[0172] The device control method program for Mini LED display stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve:

[0173] receiving a display control instruction, and determining a device to be controlled based on the display control instruction, wherein the device to be controlled includes a plurality of areas to be controlled;

[0174] Using the device to be controlled, playing the pre-acquired training video set to obtain a playback feature vector set, and calculating a video similarity set of the training video set, wherein the playback feature vectors in the playback feature vector set include: a playback brightness vector and a playback color vector;

[0175] A fitness value set of the training video set is obtained using a preset questionnaire, and a key-value pairing is performed on each playback feature vector in the playback feature vector set according to the fitness value set to obtain a fitness key-value group set;

[0176] Extracting training fitness key value groups in sequence from the fitness key value group set, and determining training feature vectors in the training fitness key value groups, wherein the training feature vectors include: a brightness training vector and a color training vector;

[0177] Initializing a pre-constructed particle swarm based on the training feature vector and the video similarity set to obtain an initial particle swarm, wherein the particle swarm includes a plurality of particles;

[0178] Iterate the initial particle swarm to obtain the optimal position, determine the optimal brightness vector based on the optimal position, summarize the optimal brightness vectors, and obtain the optimal brightness vector set;

[0179] Based on the training video set, the optimal brightness vector set is classified to obtain the same-video brightness vector set. According to the same-video brightness vector set, the training video set is played to obtain the fitness adjustment key value set.

[0180] The adjusted fitness key value set is used as the fitness key value set, and the step of obtaining the fitness value set of the training video set using the preset questionnaire is returned until each fitness value in the fitness value set is greater than the preset fitness threshold, and the optimal fitness key value set is obtained, and the control of the device to be controlled is completed based on the optimal fitness key value set.

[0181] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0182] Furthermore, if the modules / units integrated into the electronic device 1 are implemented as software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. The computer-readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0183] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program. When the computer program is executed by a processor of an electronic device, the computer program can implement:

[0184] receiving a display control instruction, and determining a device to be controlled based on the display control instruction, wherein the device to be controlled includes a plurality of areas to be controlled;

[0185] Using the device to be controlled, playing the pre-acquired training video set to obtain a playback feature vector set, and calculating a video similarity set of the training video set, wherein the playback feature vectors in the playback feature vector set include: a playback brightness vector and a playback color vector;

[0186] A fitness value set of the training video set is obtained using a preset questionnaire, and a key-value pairing is performed on each playback feature vector in the playback feature vector set according to the fitness value set to obtain a fitness key-value group set;

[0187] Extracting training fitness key value groups in sequence from the fitness key value group set, and determining training feature vectors in the training fitness key value groups, wherein the training feature vectors include: a brightness training vector and a color training vector;

[0188] Initializing a pre-constructed particle swarm based on the training feature vector and the video similarity set to obtain an initial particle swarm, wherein the particle swarm includes a plurality of particles;

[0189] Iterate the initial particle swarm to obtain the optimal position, determine the optimal brightness vector based on the optimal position, summarize the optimal brightness vectors, and obtain the optimal brightness vector set;

[0190] Based on the training video set, the optimal brightness vector set is classified to obtain the same-video brightness vector set. According to the same-video brightness vector set, the training video set is played to obtain the fitness adjustment key value set.

[0191] The adjusted fitness key value set is used as the fitness key value set, and the step of obtaining the fitness value set of the training video set using the preset questionnaire is returned until each fitness value in the fitness value set is greater than the preset fitness threshold, and the optimal fitness key value set is obtained, and the control of the device to be controlled is completed based on the optimal fitness key value set.

[0192] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only exemplary, and actual implementations may have other division methods.

[0193] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0194] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0195] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0196] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A device control method for Mini LED display, characterized in that: The method comprises: receiving a display control instruction, and determining a device to be controlled based on the display control instruction, wherein the device to be controlled includes a plurality of areas to be controlled; Using the device to be controlled, playing the pre-acquired training video set to obtain a playback feature vector set, and calculating a video similarity set of the training video set, wherein the playback feature vectors in the playback feature vector set include: a playback brightness vector and a playback color vector; A fitness value set of the training video set is obtained using a preset questionnaire, and a key-value pairing is performed on each playback feature vector in the playback feature vector set according to the fitness value set to obtain a fitness key-value group set; Extracting training fitness key value groups in sequence from the fitness key value group set, and determining training feature vectors in the training fitness key value groups, wherein the training feature vectors include: a brightness training vector and a color training vector; Initializing a pre-constructed particle swarm based on the training feature vector and the video similarity set to obtain an initial particle swarm, wherein the particle swarm includes a plurality of particles; Iterate the initial particle swarm to obtain the optimal position, determine the optimal brightness vector based on the optimal position, summarize the optimal brightness vectors, and obtain the optimal brightness vector set; Based on the training video set, the optimal brightness vector set is classified to obtain the same-video brightness vector set. According to the same-video brightness vector set, the training video set is played to obtain the fitness adjustment key value set. The adjusted fitness key value set is used as the fitness key value set, and the step of obtaining the fitness value set of the training video set using the preset questionnaire is returned until each fitness value in the fitness value set is greater than the preset fitness threshold, and the optimal fitness key value set is obtained, and the control of the device to be controlled is completed based on the optimal fitness key value set.

2. The device control method for Mini LED display according to claim 1, wherein: The method of using the device to be controlled to play the pre-acquired training video set to obtain a playback feature vector set includes: For each training video in the training video set, perform the following operations: Setting a start time for playing, and at the start time, playing the training video using the multiple areas to be controlled in the device to be controlled; According to the start time of playing, each area to be controlled is sampled in the playing step to obtain multiple playing brightness values ​​and multiple playing color values, wherein the playing brightness values ​​and the playing color values ​​correspond to the areas to be controlled one by one; Obtaining a playback feature vector according to the plurality of playback brightness values ​​and the plurality of playback color values, wherein the playback feature vector includes: a playback brightness vector and a playback color vector; Calculate the intermediate sampling time according to the preset sampling interval and the start time of playback; The intermediate sampling moment is used as the start playback moment, and the process returns to the step of sampling each area to be controlled in the playback step according to the start playback moment, until the intermediate sampling moment is not less than the preset end playback moment; The playback feature vectors are summarized to obtain a playback feature vector group, and the playback feature vector group corresponding to each training video is merged to obtain a playback feature vector set.

3. The device control method for Mini LED display according to claim 2, wherein: The calculating of the video similarity set of the training video set includes: Extracting a first training video from a training video set and constructing a video feature matrix of the first training video, wherein the video feature matrix includes color features; Eliminate the first training video from the training video set to obtain an eliminated training video set, and sequentially extract comparison training videos from the eliminated training video set; Constructing a comparative feature matrix of the comparative training video, and calculating video similarity based on the video feature matrix and the comparative feature matrix; The eliminated training video set is used as the training video set, and the step of extracting the first training video in the training video set is returned to, until the eliminated training video set is an empty set; The video similarities are aggregated to obtain a video similarity set.

4. The device control method for Mini LED display according to claim 3, wherein: The step of constructing a video feature matrix of a first training video includes: According to the preset number of pictures, a single-frame picture set is extracted from the first training video; Performing feature extraction on each single-frame image in the single-frame picture set to obtain a picture feature vector set, wherein the feature extraction includes: color feature extraction, and the picture feature vectors in the picture feature vector set correspond one-to-one to the single-frame pictures in the single-frame picture set; Construct a video feature matrix based on the image feature vector set.

5. The device control method for Mini LED display according to claim 4, wherein: The method of obtaining the fitness value set of the training video set by using a preset questionnaire includes: Extract the completed playback videos in the training video set in sequence; Identify multiple video viewers based on the completed video playback, and send questionnaires to the multiple video viewers to obtain multiple viewing experience data; Calculate the average value based on multiple viewing experience data to obtain comprehensive experience data, and calculate the fitness value based on the comprehensive experience data; The fitness value corresponding to each completed video is summarized to obtain a fitness value set.

6. The device control method for Mini LED display according to claim 5, wherein: The pre-constructed particle swarm is initialized based on the training feature vector and the video similarity set to obtain an initial particle swarm, including: Eliminate the training fitness key value group from the fitness key value group set to obtain a comparison fitness key value group set; Extracting contrast fitness key value groups in sequence from the contrast fitness key value group set, and determining contrast parameter groups in the contrast fitness key value groups, wherein the contrast parameter groups include: a brightness contrast vector, a color contrast vector, and a contrast fitness value; Extracting particles in sequence from the particle group to generate initial velocities of the particles; generating an initial query vector based on a brightness training vector in the training feature vector, and recording the initial query vector as an initial position; According to the initial query vector, determine the fitness value weight and comparison similarity of the comparison fitness key value group; Summarizing the fitness value weight, comparative similarity, and comparative fitness value of each comparative fitness key value group in the comparative fitness key value group set to obtain a fitness value weight set, a comparative similarity set, and a comparative fitness value set; Calculate the initial fitness value according to the fitness value weight set, the comparison similarity set and the comparison fitness value set; Based on the initial fitness value, the initial position and the initial velocity, initial particles are generated, and the initial particles are aggregated to obtain an initial particle group.

7. The device control method for Mini LED display according to claim 6, wherein: Determining the fitness value weight and the comparison similarity of the fitness key value group based on the initial query vector includes: Calculate the fitness value weight according to the brightness contrast vector, the initial query vector, the color training vector and the color contrast vector; The main training video and the comparative training video corresponding to the training fitness key group and the comparative fitness key group are respectively determined, and the comparative similarity between the main training video and the comparative training video is identified in a video similarity set.

8. The device control method for Mini LED display according to claim 7, wherein: The step of calculating the fitness value weight according to the brightness contrast vector, the initial query vector, the color training vector, and the color contrast vector includes: The fitness value weight is calculated using the following formula: in, represents the fitness value weight, represents the activation function, represents the brightness contrast vector, represents the initial query vector, The vector dimension representing the brightness contrast vector, represents the color contrast vector, represents the color training vector, The dimension of the vector representing the color contrast vector.

9. The device control method for Mini LED display according to claim 8, wherein: The calculating of the initial fitness value comprises: According to the fitness value weight set, the comparison similarity set and the comparison fitness value set, the initial fitness value is calculated using the following formula: in, represents the initial fitness value, Indicates the number of contrast similarities in the contrast similarity set, Indicates the first Comparative similarity, Indicates the first Fitness value weights, Indicates the first Comparative fitness values.

10. A device control system for Mini LED display, characterized in that: The system comprises: a playback vector extraction module, configured to receive a display control instruction, determine a device to be controlled based on the display control instruction, wherein the device to be controlled includes multiple areas to be controlled, use the device to be controlled to play a pre-acquired training video set to obtain a playback feature vector set, and calculate a video similarity set for the training video set, wherein the playback feature vectors in the playback feature vector set each include: a playback brightness vector and a playback color vector; A fitness survey module is used to obtain a fitness value set of a training video set using a preset questionnaire, perform key-value pairing on each playback feature vector in the playback feature vector set based on the fitness value set to obtain a fitness key value group set, sequentially extract training fitness key value groups from the fitness key value group set, and determine training feature vectors in the training fitness key value groups, wherein the training feature vectors include: a brightness training vector and a color training vector; An optimal brightness determination module is used to initialize a pre-constructed particle swarm based on the training feature vector and the video similarity set to obtain an initial particle swarm, wherein the particle swarm includes multiple particles, iterate the initial particle swarm to obtain an optimal position, and determine an optimal brightness vector based on the optimal position, and summarize the optimal brightness vectors to obtain an optimal brightness vector set; The video playback return module is used to classify the optimal brightness vector set based on the training video set to obtain the same-video brightness vector group set, play the training video set according to the same-video brightness vector group set, obtain the adjustment fitness key value group set, use the adjustment fitness key value group set as the fitness key value group set, and return to the step of obtaining the fitness value set of the training video set using a preset questionnaire until each fitness value in the fitness value set is greater than the preset fitness threshold, and the optimal fitness key value group set is obtained.

Images