A backlight control system and method for an LED LCD screen

Abstract

This invention relates to the field of intelligent control and discloses a backlight control system and method for an LED LCD screen. The control system includes a multi-sensor information acquisition module, a control module, a driving circuit module, a brightness control module, and a backlight module. The control method includes an intelligent computing decision unit, a rule queue generation mechanism, and a fuzzy synthesis process for three rule modes. This control system and method are of great significance in solving power consumption management control, heat dissipation management control, improving the user experience of display devices, saving energy, and increasing the lifespan of LED backlights.

Description

Technical Field

[0001] This invention relates to the field of intelligent control, and more specifically, to a backlight control system and method for an LED LCD screen. Background Technology

[0002] LED backlights are an indispensable component in display devices such as LCD monitors, providing backlighting to increase brightness and contrast. Traditional LED backlight control schemes are usually based on fixed preset brightness settings or simple manual adjustments, which cannot flexibly adapt to actual outdoor scene requirements and lack effective power management control.

[0003] Furthermore, prolonged operation can easily lead to a series of problems, such as overheating and burning out components. Although current LED backlight control systems can control the on / off state of the LED backlight by controlling the circuit, previous control systems could not adjust the heat dissipation rate of the LED backlight, which could easily cause damage to the LED backlight due to inadequate heat dissipation during use.

[0004] Traditionally, power management and thermal management are distributed across different modules. There is a need for an optimized LED backlight control system that can simultaneously meet user-defined backlight brightness management, intelligent adaptive power management, and avoidance of high-temperature overload using a single control structure. This is significant for improving the user experience of display devices, saving energy, and extending the lifespan of LED backlights. Therefore, we propose a backlight control system and method for LED LCD screens. Summary of the Invention

[0005] The purpose of this invention is to provide a backlight control system and method for LED LCD screens to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a backlight control system for an LED LCD screen, comprising:

[0007] The multi-sensor information acquisition module is used to detect and collect a series of sensor information closely related to common outdoor scenarios;

[0008] The control module can receive information from the information acquisition module, generate feedback control signals, and connect them to the drive circuit module.

[0009] The drive circuit module receives feedback signals generated by the control module and drives the brightness and hue calling module.

[0010] The brightness and hue adjustment module is used to determine, based on the generated feedback signal, whether the brightness value of the LED backlight should be increased, maintained, or decreased, or whether the hue value should be kept bright or dim.

[0011] The backlight module is used to receive adjustment information and make corresponding adjustments.

[0012] Preferably, the multi-sensor information acquisition module includes:

[0013] Used to receive user-defined user interfaces;

[0014] An ambient light sensor used to receive ambient light intensity;

[0015] Cameras used to receive pedestrian or vehicle traffic flow data;

[0016] A temperature sensor used to receive the temperature of the device.

[0017] Preferably, the control module includes:

[0018] Intelligent computing decision-making unit used to receive sensing information and generate control signals according to intelligent algorithms;

[0019] A rule queue generation mechanism for generating multi-level rule queues;

[0020] A mechanism used to transmit control signals to the drive circuit.

[0021] Preferably, the driving circuit module and the brightness and hue adjustment module can receive control signals to control and adjust the brightness and hue of the backlight.

[0022] A backlight control method for an LED LCD screen includes the following steps:

[0023] Step 1: After the sensory information collection data is cleaned and its features are abstracted, it is divided according to the dimension of the feature vector and applied to different intelligent computing units. Among them, high-dimensional data uses a neural network model for feature extraction and discrimination, while low-dimensional data uses a fuzzy system for feature extraction and discrimination.

[0024] Step 2: To ensure that multi-view, multi-modal data can collaboratively learn complementary and efficient features, gradient updates adopt a mechanism similar to that of a parameter server.

[0025] Step 3: Specifically, it is divided into two parts. Each local intelligent computing unit only calculates the dataset related to itself and generates local gradients. These gradient information are aggregated into a common node and accumulated. Then, this common node updates the overall weight parameters according to the common gradient and distributes the overall parameters to different local intelligent computing units according to the corresponding relationship.

[0026] Step 4: After reaching the desired error, the four local intelligent computing units generate four exclusive feedback generation signals. These four feedback generation signals will then be further used to generate corresponding rule queues through fuzzy synthesis.

[0027] Preferably, the multi-level rule queue generation mechanism includes: a three-level rule queue based on a set mode, consisting of three modes: user-defined mode, performance mode, and power-saving mode. The user-defined mode is used for users' fine-grained customization needs, the high-performance mode is used when the power supply is sufficient, and the power-saving mode is used for unstable power supply methods using solar energy + battery modules. The mode synthesis method uses a hierarchical fuzzy system, which consists of a hierarchical synthesis method of "main feedback synthesis", "secondary feedback synthesis", and "final feedback synthesis".

[0028] Preferably, the user-defined mode, performance mode, and power-saving mode in the multi-level rule queue generation mechanism have the following steps:

[0029] Power saving mode:

[0030] The main feedback synthesis is achieved by first performing fuzzy synthesis of "user-defined information" and "temperature information". This design is because user-defined information and temperature information play the most important roles in power-saving mode.

[0031] Secondary feedback synthesis involves fuzzy synthesis of "ambient light information" and "pedestrian and vehicle traffic information (which can be collected by sound sensors or cameras, etc.)". It is called secondary feedback information because their feedback results are only used to fine-tune the results of the main feedback.

[0032] The final feedback synthesis is used to generate the final feedback signal. Its synthesis logic is to synthesize the main feedback generation signal and the negative feedback generation signal. The final synthesis result is a set of scalar information.

[0033] Performance Mode:

[0034] The main feedback synthesis is a fuzzy composite of "user-defined information" and "ambient light information"; the secondary feedback synthesis is a composite of "temperature information" and "pedestrian and vehicle traffic information"; and the final synthesis is a further composite of the results of the main feedback information and the secondary feedback information.

[0035] User-defined mode:

[0036] The main feedback consists of "user-defined information" as the sole input; the secondary feedback consists of three inputs: "ambient light information," "pedestrian and vehicle traffic information," and "temperature information"; and the final result of synthesizing the main feedback information and the secondary feedback information is further combined.

[0037] Compared with the prior art, the control system and method provided by the present invention have the following beneficial effects:

[0038] 1. The control system and method receive various types of information from the information acquisition module, providing an integrated, customizable, scalable, and adaptive control method for various conditions, and offering on-demand power management and intelligent adjustment capabilities for the backlight.

[0039] 2. This control system and method not only ensure better visual effects and effectively reduce the energy consumption of LED backlights, but also effectively prevent the backlights from being damaged due to untimely heat dissipation during use, thereby improving the service life of LED backlights.

[0040] 3. This control system and method provide a multi-perspective, multi-modal, and multi-intelligent representation multi-sensory information fusion mechanism. Through the collaborative learning of these sensory information, a pre-loadable multi-level rule queue is generated. This shortens the control link, separates training and inference, effectively saves resources, reduces power consumption, and improves the robustness and stability of the system. Attached Figure Description

[0041] The accompanying drawings, which are included in and form part of this specification, illustrate exemplary embodiments, features, and aspects of this application together with the specification and serve to explain the principles of this application.

[0042] Figure 1 An overall block diagram of an LED backlight control system according to an embodiment of this application is shown;

[0043] Figure 2 The framework of the control module shown in the LED backlight control system according to an embodiment of this application is illustrated.

[0044] Figure 3 An example of fuzzy synthesis for generating a multi-level rule queue is shown in the control module of an LED backlight control system according to an embodiment of this application. Detailed Implementation

[0045] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are also within the scope of protection of this application.

[0046] Various exemplary embodiments, features, and aspects of this application will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0047] Furthermore, to better illustrate this application, numerous specific details are provided in the following detailed embodiments. Those skilled in the art should understand that this application can be implemented without certain specific details. In some instances, methods, means, components, and circuits well-known to those skilled in the art have not been described in detail in order to highlight the main points of this application.

[0048] Figure 1 This is a schematic block diagram of an LED LCD screen backlight control system according to an embodiment of this application. Figure 1 As shown, it includes an information acquisition module, a control module, a drive circuit module, a brightness control module, and a backlight group.

[0049] Specifically, the information acquisition module includes and processes the following scenarios: ① When the ambient light changes from bright to dark or from dark to bright, the advertising screen has a corresponding adaptive brightness adjustment function. The acquisition method is an ambient light sensor. ② When there is a large flow of people and vehicles at night, the advertising screen should have a striking and vibrant brightness. The acquisition method is a camera, sound sensor, or on-site survey data. ③ When prolonged operation causes significant heat generation in the components, the advertising screen should have appropriate adaptive power consumption reduction to avoid prolonged high-temperature overload and component burnout. The acquisition method is a temperature sensor. ④ When users want to perform fine-tuned brightness control, the advertising screen should be able to meet the user's customization needs. The acquisition method is a user interface.

[0050] Specifically, the control module is used to process data samples from cameras / sensors / on-site data that have different perspectives but are inherently related in some sense. It can effectively fuse and generate corresponding control signals. It adopts a multi-view collaborative learning mechanism to generate the final control rule queue.

[0051] Correspondingly, Figure 2 As shown, based on the requirements of the control objective, a multi-sensor information acquisition module is used to collect relevant information and aggregate it to generate datasets from the corresponding perspectives. Generally, these datasets are divided into two categories after processing: high-dimensional data, such as a 28*28 image which can be considered as 784-dimensional data. The implementation method mainly involves a neural network integrating dimensionality reduction and feature extraction. Low-dimensional data, mainly sensor or statistical sample data, is characterized by single or limited dimensions, lacking precise and sufficient dimensions to meet the requirements. This type of data sample is more suitable for using fuzzy systems as a feature extraction and decision-making method. y is a feature vector abstracted from a low-dimensional or high-dimensional dataset, f is a neural network model or a fuzzy system model, and y is the result of the data sample output by the corresponding model.

[0052] Specifically, the fusion of neural network models or fuzzy system models is reflected in the use of a multi-perspective collaborative learning mechanism. Unlike the traditional definition of "single samples from different perspectives," this embodiment extends the concept of multi-perspective to refer to different decision-making methods under the same objective. Collaborative learning means that the optimization mechanism of the multi-perspective model adopts joint training rather than combining the training of each individual model. For the four perspectives described in this embodiment, the joint training mechanism formula is shown in (1):

[0053] L=L1+L2+L3+L4 (1)

[0054] Where L is the overall optimization loss function, and L1 to L4 are the loss functions based on perspectives 1 to 4 in the corresponding intelligent modes, respectively. The joint optimization mechanism allows intelligent computing decision units to fully utilize the diversity and complementarity of data sample representations from different perspectives to construct globally optimal customized decision unit parameters.

[0055] Specifically, to further refine formula (1), firstly, the optimization mechanism of a single intelligent control algorithm typically has an optimization mechanism as described in formula (2). The perceived information collected through the information acquisition module is abstracted into individual data. The input for individual samples is typically in high-dimensional vector form. i is the output of the sample individual, usually in scalar form. w represents the parameters of the neural network model or fuzzy system model after training. Ω is the regularization term that controls the fuzzy complexity.

[0056]

[0057] when When the data sources are heterogeneous, the above can be broken down into optimization objectives from four perspectives as shown in this embodiment. The heterogeneous dataset portion can be processed by different control methods in the intelligent computing decision unit; in this embodiment, the processing is primarily based on dimension. Specifically, information from images is processed by the neural network module, and information from sensors is processed by the fuzzy system.

[0058] Combining formula (1), formula (2) is further divided into the form described in formula (3) according to the heterogeneous dataset, where l1 to l4 are the optimized forms after splitting.

[0059]

[0060] When the dataset is split into different intelligent algorithms, each control algorithm actually only receives a portion of the dataset and weight information. To take advantage of collaborative learning, the training of formula (3) adopts a parameter server mechanism, that is, each control algorithm only uses the corresponding perceptual information and then calculates the gradient information related to its own perceptual information. However, the weight update needs to be aggregated on a common parameter server for global weight update. The gradient update calculation process for each individual l is shown in formula (4). Wherein, g r (t) The gradient information at time t is calculated based on its corresponding dataset and weight information. r (t) This represents the local weight information corresponding to time t.

[0061]

[0062] The parameter server summarizes the gradients of the four objective optimization functions, calculates the total gradient sum, and then uses the gradient descent algorithm to calculate the gradient for the next round. Each control algorithm then retrieves its corresponding gradient and continues the update process. The calculation process is shown in formula (5). Where g (t) Let w be the global gradient at time t. (t) This represents the global weight information at time t.

[0063]

[0064] The control algorithm for each viewpoint generates a corresponding feedback signal. In this implementation, a total of four control signals are generated.

[0065] Accordingly, the feedback signals generated by the intelligent computing decision-making unit can be further fused using a fuzzy system to achieve more accurate control over backlighting, such as hue and power consumption.

[0066] In this implementation, the rule queue consists of three levels. Decision selection is achieved by polling the rule queue and setting corresponding modes based on priority. Rule 1 has the highest priority, corresponding to the user mode with the highest weight, while allowing for some modification of other parameters. Different modification levels constitute different individuals within Rule 1. Rule 2 has a second-highest priority, corresponding to the optimal system selected by the decision optimization formula (1) under default settings. This can be considered a "high-performance mode / vibrant mode" for use when power supply is stable. Similarly, different modification levels also constitute different individuals within Rule 2. Rule 3, compared to Rule 2, mainly focuses on "power-saving mode," suitable for outdoor conditions such as highways and situations with unstable power supply such as solar energy or batteries.

[0067] Taking "Power Saving Mode" as an example, the fuzzy rule synthesis strategy used for the rule queue generation mechanism is as follows: ① Main Feedback Synthesis: Fuzzy synthesis is first performed between "user-defined information" and "temperature information." This design is because user-defined information and temperature information play the most important roles in power saving mode. ② Secondary Feedback Synthesis: Fuzzy synthesis is performed between "ambient light information" and "pedestrian and vehicle traffic information (which can be collected by sound sensors or cameras, etc.)." These are secondary feedback information because their feedback results are only used to fine-tune the main feedback result. ③ Final Feedback Synthesis: Used to generate the final feedback signal. Its synthesis logic involves the final synthesis of the main feedback generated signal and the negative feedback generated signal. The final synthesis result is a set of scalar information. The overall synthesis logic is as follows: Figure 3 As shown. Each level of the rule queue uses only the same fuzzy synthesis logic, but allows for the generation of multiple control values ​​depending on the degree of leniency in control.

[0068] The driving circuit module and brightness control module described in this embodiment are driven by the control signal generated by the control module and applied to the brightness control module. With the help of feedback parameters, the warm and cool color modes can be controlled by adjusting the light transmittance, and the brightness can be controlled by adjusting the power consumption, thereby controlling the different modes of the backlight in general.

[0069] The backlight module described in this embodiment consists of multiple LEDs forming an LED group. The LED backlight is used to emit light of different brightness and hue.

Claims

1. A backlight control method for an outdoor LED LCD advertising screen, characterized in that, Includes the following steps: Step 1: After the sensory information collection data is cleaned and its features are abstracted, it is divided according to the dimension of the feature vector and applied to different intelligent computing units. Among them, high-dimensional data uses a neural network model for feature extraction and discrimination, while low-dimensional data uses a fuzzy system for feature extraction and discrimination. Step 2: To ensure that multi-view, multi-modal data can collaboratively learn complementary and efficient features, gradient updates adopt a mechanism similar to that of a parameter server; Step 3: Specifically, it is divided into two parts. Each local intelligent computing unit only calculates the dataset related to itself and generates local gradients. These gradient information are aggregated into a common node and accumulated. Then, this common node updates the overall weight parameters according to the common gradient and distributes the overall parameters to different local intelligent computing units according to the corresponding relationship. Step 4: After reaching the desired error, the four local intelligent computing units generate four feedback generation signals. These four feedback generation signals will be further used to generate corresponding rule queues using fuzzy synthesis. The four local intelligent computing units correspond to four perspectives: ambient light, pedestrian and vehicle traffic, temperature, and user-defined mode. The generated rule queue includes a three-level rule queue based on a set mode, consisting of three modes: user-defined mode, performance mode, and power-saving mode. The user-defined mode is used for users' fine-grained customization needs, the high-performance mode is used when the power supply is sufficient, and the power-saving mode is used for unstable power supply methods using solar energy + battery modules. The mode synthesis method uses a hierarchical fuzzy system, which consists of a hierarchical synthesis method of main feedback synthesis, secondary feedback synthesis, and final feedback synthesis.

2. The backlight control method for an outdoor LED LCD advertising screen according to claim 1, wherein the three modes of the rule queue are as follows: Power saving mode: main feedback synthesis, where user-defined information and temperature information are first fuzzily synthesized. This design is because user-defined information and temperature information play the most important weight in power saving mode; secondary feedback synthesis, where ambient light information and pedestrian and vehicle traffic information are fuzzily synthesized. The reason for secondary feedback information is that their feedback results are only used to fine-tune the results of the main feedback; final feedback synthesis, used to generate the final feedback signal. Its synthesis logic is the final synthesis of the main feedback generated signal and the negative feedback generated signal. The final synthesis result is a set of scalar information. Performance Mode: Main feedback synthesis, which uses user-defined information and ambient light information for fuzzy synthesis; Secondary feedback synthesis, which uses temperature information and pedestrian and vehicle traffic information for synthesis; Final synthesis, which further synthesizes the results of the main feedback information and the secondary feedback information; User-defined mode: The main feedback uses user-defined information as the only input; The secondary feedback consists of three inputs: ambient light information, pedestrian flow information, vehicle flow information, and temperature information; the final result of synthesizing the primary feedback information and the secondary feedback information is further combined.

3. A backlight control system for an outdoor LED LCD screen, used to execute the method as described in any one of claims 1-2, characterized in that, include: The multi-sensor information acquisition module is used to detect and collect a series of sensor information closely related to common outdoor scenarios; The control module can receive information from the information acquisition module, generate feedback control signals, and connect them to the drive circuit module. The drive circuit module receives feedback signals generated by the control module and drives the brightness and hue calling module. A brightness and hue adjustment module is used to determine, based on the generated feedback signal, whether the brightness value of the LED backlight should be increased, maintained, or decreased, or whether the hue value should be kept bright or dim. The backlight module is used to receive adjustment information and make corresponding adjustments.

4. A backlight control system for an outdoor LED LCD screen according to claim 3, characterized in that, The multi-sensor information acquisition module includes: Used to receive user-defined user interfaces; An ambient light sensor used to receive ambient light intensity; Cameras used to receive pedestrian or vehicle traffic flow data; A temperature sensor used to receive the temperature of the device.

5. A backlight control system for an outdoor LED LCD screen according to claim 4, characterized in that... The control module includes: Intelligent computing decision-making unit used to receive sensing information and generate control signals according to intelligent algorithms; A rule queue generation mechanism for generating multi-level rule queues; A mechanism used to transmit control signals to the drive circuit.

6. The backlight control system for an outdoor LED LCD screen according to claim 5, characterized in that, The drive circuit module and the brightness and hue adjustment module can receive control signals to control and adjust the brightness and hue of the backlight.

Images