LED illumination intelligent control system and method based on multi-condition decision

Abstract

The invention discloses an LED illumination intelligent control system and method based on multi-condition decision, and relates to the technical field of intelligent illumination control, and the method comprises the steps: collecting and preprocessing environment data, and converting the environment data into a four-dimensional quantum state tensor through quantum feature mapping; analyzing various environmental data in the four-dimensional quantum state tensor, and generating a regional brightness target value; mapping the regional brightness target value into a PWM duty ratio, and executing LED illumination control according to the PWM duty ratio; the execution effect of LED illumination control is monitored through a photoresistor, deviation judgment is carried out on the execution effect and the regional brightness target value, and a judgment result is output; and according to a judgment result, dividing a conflict region, coding the PWM duty ratio of the conflict region into a quantum entanglement state, decomposing the quantum entanglement state, and generating a cross-region brightness adjustment rule. According to the method, the hyperedge connection strategy is defined by analyzing the environmental data, so that the accuracy of the regional brightness target value is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent lighting control, and in particular to an LED lighting intelligent control system and method based on multi-condition decision-making. Background Art

[0002] In recent years, LED intelligent lighting control technology has gradually evolved towards multi-source environmental perception and dynamic collaborative optimization. With the deep integration of the Internet of Things and edge computing technologies, the capabilities of multi-sensor data acquisition and high-dimensional feature extraction have been significantly improved, providing multi-dimensional parameter support for brightness regulation in complex scenarios. At the environmental perception level, the real-time fusion technology of heterogeneous data such as light intensity, user distribution, temperature, and grid load has become increasingly mature. Combined with deep learning models, such as the environmental feature modeling methods of convolutional neural networks and graph attention mechanisms, it has been able to achieve dynamic brightness adaptation in local areas. In addition, the regional collaborative optimization framework based on graph theory further improves the adaptability of multi-region linkage through the quantitative description of the interaction weights between nodes.

[0003] However, the existing technologies have low capabilities in resolving the relationships of multi-source data and insufficient cross-region dynamic conflict resolution. Traditional data fusion methods have insufficient capabilities in analyzing the non-linear coupling relationships of multi-modal parameters such as light, temperature, and grid load, and it is difficult to accurately quantify the global collaborative weights through classical algorithms. Although non-linear dimensionality reduction technologies have been tried to enhance the representation ability of parameter associations by constructing implicit feature spaces, however, such methods have high computational complexities for high-dimensional heterogeneous data and rely on a large amount of labeled data to train models, resulting in difficulties in real-time updating of collaborative weights in dynamic scenarios. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an LED lighting intelligent control method based on multi-condition decision-making to solve the problems of low capabilities in resolving the relationships of multi-source data and insufficient cross-region dynamic conflict resolution.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an intelligent control method for LED lighting based on multi - condition decision - making, which includes collecting environmental data and performing pre - processing, converting the environmental data into a four - dimensional quantum state tensor through quantum feature mapping, where the environmental data includes regional data, illumination data, user density data, temperature data, and power grid load data; analyzing each item of environmental data in the four - dimensional quantum state tensor, defining a hyper - edge connection strategy, adjusting the LED lighting requirements according to the hyper - edge connection strategy, and generating a regional brightness target value; mapping the regional brightness target value to a PWM duty cycle and performing LED lighting control according to the PWM duty cycle; monitoring the execution effect of the LED lighting control through a photosensitive resistor, making a deviation determination between the execution effect and the regional brightness target value, and outputting a determination result; dividing the conflict area according to the determination result, encoding the PWM duty cycle of the conflict area into a quantum entanglement state, and decomposing the quantum entanglement state to generate a cross - regional brightness adjustment rule.

[0008] As a preferred solution of the intelligent control method for LED lighting based on multi - condition decision - making according to the present invention, where: the specific steps of converting the environmental data into a four - dimensional quantum state tensor through quantum feature mapping are as follows:

[0009] Taking the pre - processed environmental data as an independent one - dimensional data sequence;

[0010] Extracting the environmental parameter values of the illumination data, user density data, temperature data, and power grid load data in the one - dimensional data sequence through data indexing;

[0011] Mapping the environmental parameter values to a one - dimensional quantum state sequence by using quantum amplitude encoding;

[0012] Aggregating multiple one - dimensional quantum state sequences through tensor product to generate a four - dimensional quantum state tensor.

[0013] As a preferred solution of the intelligent control method for LED lighting based on multi - condition decision - making according to the present invention, where: the specific steps of analyzing each item of environmental data in the four - dimensional quantum state tensor and defining a hyper - edge connection strategy are as follows:

[0014] Classifying the four - dimensional quantum state tensor according to the regional boundary in the regional data to generate functional regions;

[0015] Defining each functional region as a regional node of a hyper - graph;

[0016] Taking the illumination data, user density data, temperature data, and power grid load data as environmental attributes of the hyper - graph regional nodes;

[0017] Pairing the regional nodes with the neighboring regional nodes to generate a region - neighborhood node group, and calculating the intensity covariance of each environmental attribute of the region - neighborhood node group;

[0018] Set the intensity covariance threshold, and determine whether the intensity covariance is greater than the intensity covariance threshold;

[0019] If the intensity covariance is greater than the intensity covariance threshold, then take the region-domain node group as a hyperedge, and take the intensity covariance value as the hyperedge weight.

[0020] As a preferred solution of the LED lighting intelligent control method based on multi-condition decision-making according to the present invention, wherein: formulating a brightness adjustment rule according to the hyperedge weight, balancing the brightness requirements of each region node of the LED lighting, and outputting a region brightness target value. The specific steps are as follows:

[0021] Classify the hyperedge weights according to the environmental attribute types, sum up the hyperedge weights of each type of environmental attribute, and generate a global attribute weight;

[0022] Perform a weighted sum of the global attribute weight and the environmental attributes of each region node to obtain the region brightness demand value of each region node;

[0023] Take the hyperedge weight as the cooperation intensity of each region node, and map the region brightness demand value to a brightness tendency value;

[0024] Define a brightness adjustment rule based on the cooperation intensity and the brightness tendency value;

[0025] Adjust the initial region brightness demand value according to the brightness adjustment rule, and output the region brightness target value.

[0026] As a preferred solution of the LED lighting intelligent control method based on multi-condition decision-making according to the present invention, wherein: mapping the region brightness target value to a PWM duty cycle, and performing LED lighting control according to the PWM duty cycle. The specific steps are as follows:

[0027] Map the region brightness target value to a PWM duty cycle through the LED lighting linear relationship;

[0028] Send the PWM duty cycle to the LED controller through the SPI protocol;

[0029] Set the PWM period according to the PWM frequency range inside the LED controller;

[0030] Based on the PWM period and the PWM duty cycle, calculate the high-level time of the PWM duty cycle to drive the LED brightness control.

[0031] As a preferred solution of the LED lighting intelligent control method based on multi-condition decision-making according to the present invention, wherein: monitoring the execution effect of the LED lighting control through a photoresistor, and performing a deviation determination on the execution effect and the region brightness target value, and outputting a determination result. The specific steps are as follows:

[0032] Monitor the light intensity of LED lighting and generate real-time LED lighting brightness values;

[0033] Calculate the deviation between the real-time LED lighting brightness value and the regional brightness target value, and generate a brightness deviation value;

[0034] Set a brightness deviation threshold, and make a deviation determination between the brightness deviation value and the brightness deviation threshold;

[0035] When the brightness deviation value does not exceed the brightness deviation threshold, it is determined that the regional brightness target value does not need to be adjusted;

[0036] When the brightness deviation value exceeds the brightness deviation threshold, it is determined that the regional brightness target value needs to be adjusted, and the regional nodes are marked.

[0037] As a preferred solution of the LED lighting intelligent control method based on multi-condition decision described in the present invention, wherein: dividing the conflict area according to the determination result, encoding the PWM duty cycle of the conflict area into a quantum entanglement state, and decomposing the quantum entanglement state to generate a cross-regional brightness adjustment rule. The specific steps are as follows:

[0038] Summarize the marked regional nodes according to the judgment result to generate a conflict area list;

[0039] Extract the PWM duty cycle from the conflict area list;

[0040] Encode the PWM duty cycle into a quantum entanglement state through quantum amplitude encoding and quantum qubit entanglement gate;

[0041] Decompose the quantum entanglement state through quantum principal component analysis to generate the correlation strength of the regional nodes, and adjust the LED lighting brightness across regions according to the correlation strength.

[0042] In a second aspect, the present invention provides an LED lighting intelligent control system based on multi-condition decision, including:

[0043] An acquisition module, which acquires environmental data and performs preprocessing, and converts the environmental data into a four-dimensional quantum state tensor through quantum feature mapping. The environmental data includes regional data, lighting data, user density data, temperature data, and power grid load data;

[0044] A brightness module, which analyzes the environmental data in the four-dimensional quantum state tensor, defines a hyperedge connection strategy, adjusts the LED lighting demand according to the hyperedge connection strategy, and generates a regional brightness target value;

[0045] An execution module, which maps the regional brightness target value to a PWM duty cycle and performs LED lighting control according to the PWM duty cycle;

[0046] A determination module monitors the execution effect of LED lighting control through a photosensitive resistor, determines the deviation between the execution effect and the regional brightness target value, and outputs a determination result.

[0047] An adjustment module divides the conflict area according to the determination result, encodes the PWM duty cycle of the conflict area into a quantum entanglement state, and decomposes the quantum entanglement state to generate a cross-regional brightness adjustment rule.

[0048] In a third aspect, the present invention provides a computer device, including a memory and a processor, where the memory stores a computer program, and: when the computer program is executed by the processor, any step of the LED lighting intelligent control method based on multi-condition decision as described in the first aspect of the present invention is implemented.

[0049] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored, and: when the computer program is executed by the processor, any step of the LED lighting intelligent control method based on multi-condition decision as described in the first aspect of the present invention is implemented.

[0050] The beneficial effects of the present invention are as follows: by analyzing environmental data to define the hyperedge connection strategy, the accuracy of the regional brightness target value is significantly improved. Based on the four-dimensional quantum state tensor, hyperedges are generated through the intensity covariance of the environmental attributes of regional nodes to quantify the collaborative intensity of multi-attribute superposition. Utilizing the expression ability of the hypergraph for multi-node high-order relationships, the limitation of the traditional adjacency matrix for binary linear associations is broken through, and the dynamic weight allocation of multi-environmental attributes across regions is realized, thereby generating a regional brightness target value that takes into account both local requirements and global energy consumption balance. By combining the quantization data basis and the hypergraph collaboration rule, the core framework of multi-condition decision-making is constructed, providing an accurate initial decision basis for closed-loop dimming and conflict optimization. Description of the Drawings

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0052] Figure 1 It is a flowchart of the LED lighting intelligent control method based on multi-condition decision.

[0053] Figure 2 It is a schematic diagram of the LED lighting intelligent control system based on multi-condition decision.

[0054] Figure 3 It is a flowchart of hypergraph construction and regional brightness target value calculation.

[0055] Figure 4 Flow chart adjusted for the conflict area. Specific implementation manners

[0056] In order to make the above objects, features and advantages of the present invention more obvious and understandable, the specific implementation manners of the present invention will be described in detail below with reference to the accompanying drawings of the specification.

[0057] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0058] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure or characteristic that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other from other embodiments.

[0059] Referring to Figures 1 to 4 , which is an embodiment of the present invention. This embodiment provides an intelligent control method for LED lighting based on multi-condition decision-making, including the following steps:

[0060] S1. Collect environmental data and perform preprocessing, and convert the environmental data into a four-dimensional quantum state tensor through quantum feature mapping.

[0061] Specifically, the regional data is provided by GIS. The physical boundaries and functional attributes (such as bedrooms, corridors, halls) of each region are defined in the regional data. The regional data includes the regional name, coordinate range and area information;

[0062] The illumination data is collected by illumination sensors installed in each region. For example, the sensor measures the illumination intensity of the current region at a frequency of once per minute, covering the real-time values of natural light and artificial light sources. The data is summarized to the central processor through a wireless transmission protocol;

[0063] The user density data is counted by an infrared thermal imaging camera or a Wi-Fi probe. For example, the infrared thermal imaging camera captures the personnel distribution in the region at a frequency of 30 frames per second, and the Wi-Fi probe estimates the number of people per unit area by counting the device MAC addresses. The data is encrypted and uploaded to the server;

[0064] The temperature data is collected by digital temperature sensors distributed in each region. For example, the digital temperature sensor records the real-time temperature (unit: degree Celsius) at an interval of once every 5 seconds, and the data is transmitted through a low-power Bluetooth protocol;

[0065] The grid load data is collected by smart meters, for example, smart meters record the power load value (in kilowatts) associated with the area at a cycle of once every 15 minutes, and the data is uploaded to the database via power line communication (PLC);

[0066] Preprocessing includes abnormal data filtering, missing value filling, time alignment and normalization;

[0067] Specifically, the environmental data is filtered for normal data, and the abnormal data is filtered by using statistical outlier detection methods to identify and remove invalid data caused by equipment failure or instantaneous interference. For example, for light data, a method based on dynamic thresholds is used. If the light value is lower than the minimum range of the sensor or higher than the maximum value possible in the physical scene, it is judged as abnormal. For user density data, combined with the physical capacity limit of the area, if the number of people detected exceeds the maximum carrying capacity of the area or a negative value appears, it is marked as abnormal, and the environmental data after abnormal data filtering is output, and obviously erroneous data is eliminated. Valid data points that conform to physical logic are retained to avoid noise interference and subsequent analysis;

[0068] Based on the environmental data after anomaly filtering, there are local missing values in the environmental data due to short-term sensor offline or communication interruption. The missing value filling adopts the complementary strategy of time series interpolation and spatial correlation;

[0069] Environmental data contains asynchronous data streams collected by different sensors. The timestamps of asynchronous data streams are offset due to differences in device sampling frequencies. Through time alignment operations, linear interpolation or clock synchronization protocols are used to calibrate the timestamps of all data to the reference time axis of the central processor, and output time-synchronized environmental data sets. Each parameter data has a consistent timestamp sequence, providing a basis for temporal consistency for subsequent correlation analysis.

[0070] Different environmental data have significant differences in dimensions and numerical ranges. The normalization operation maps all parameters in the environmental data to a unified interval through linear scaling.

[0071] Treat the preprocessed environmental data as an independent one-dimensional data sequence;

[0072] Extract environmental parameter values of illumination data, user density data, temperature data and power grid load data in a one-dimensional data sequence through data indexing;

[0073] Quantum amplitude coding is used to map the environmental parameter values into a one-dimensional quantum state sequence;

[0074] Aggregate multiple one-dimensional quantum state sequences by tensor product to generate a four-dimensional quantum state tensor;

[0075] Specifically, the one-dimensional quantum state sequence of light data is assigned to the first dimension, the one-dimensional quantum state sequence of user density data is assigned to the second dimension, the one-dimensional quantum state sequence of temperature data is assigned to the third dimension, and the one-dimensional quantum state sequence of grid load data is assigned to the fourth dimension. A tensor product operation is performed on the quantum state sequences of the four dimensions to generate a four-dimensional quantum state tensor jointly represented by four types of data.

[0076] S2. Analyze the environmental data in the four-dimensional quantum state tensor, define the hyperedge connection strategy, and adjust the LED lighting requirements according to the hyperedge connection strategy to generate the regional brightness target value.

[0077] Classify the four-dimensional quantum state tensor according to the regional boundaries in the regional data to generate functional regions.

[0078] Define each functional region as a regional node of the hypergraph.

[0079] Based on the differences in the regional boundaries in the regional data, different regions are divided. Each dimension of the four-dimensional quantum state tensor corresponds to an environmental data, including light data, user density data, temperature data, and grid load data. The regional data defines independent regions in the actual space, such as independent regions with different functions in a home, like bedrooms, halls, and kitchens.

[0080] Specifically, during the operation process, the four-dimensional quantum state tensor is cut along the boundaries of independent regions. The corresponding light data, user density data, temperature data, and grid load data are extracted from each independent region to generate a unique node identifier. The node identifier is bound one-to-one with the independent region name, and a set of regional nodes is output. Each node contains independent four-dimensional parameter data. For example, the bedroom node stores the light data, user density data, temperature data, and grid load data of this region, ensuring that the environmental data of different independent regions are completely isolated and avoiding calculation interference. Through the generation of regional nodes, an accurate mapping between environmental data and physical space is achieved.

[0081] Take the light data, user density data, temperature data, and grid load data as the environmental attributes of the hypergraph regional nodes.

[0082] Specifically, according to the regional nodes of the hypergraph divided, take the light data, user density data, temperature data, and grid load data within the regional nodes as the attributes of the regional nodes. Take the light data as the light attribute of the regional node, the user density data as the user density attribute of the regional node, the temperature data as the temperature attribute of the regional node, and the grid load data as the grid load attribute of the regional node to generate the environmental values of the regional nodes.

[0083] Pair the regional nodes with the neighboring regional nodes to generate a regional-neighborhood node group, and calculate the intensity covariance of the environmental attributes of the regional-neighborhood node group.

[0084] Specifically, first traverse all regional nodes, pair the regional nodes with neighboring regional nodes pairwise to generate region-domain node groups, such as region A and region B, region A and region C, and region B and region C;

[0085] Calculate the intensity covariance of the same environmental attributes within the region-domain node group. For example, calculate the temperature attribute intensity covariance, light attribute intensity covariance, user density attribute intensity covariance, and power grid load attribute intensity covariance between region A and region B. The intensity covariance calculation results include positive and negative numbers. For convenience of judgment, take the absolute value of all the obtained intensity covariances;

[0086] Set an intensity covariance threshold to determine whether the intensity covariance is greater than the intensity covariance threshold;

[0087] The intensity covariance threshold is preset by analyzing environmental data and the requirements of the actual application scenario, and is determined based on the statistical distribution characteristics of environmental attribute correlations;

[0088] If the intensity covariance is greater than the intensity covariance threshold, take the region-domain node group as a hyperedge and take the intensity covariance value as the hyperedge weight;

[0089] Specifically, when the intensity covariance is greater than or equal to the intensity covariance threshold, it indicates that the environmental attribute correlation degree of the region-domain node group is large. When the correlation degree is large, take the region-domain node group as a hyperedge and take the intensity covariance as the hyperedge weight. For example, the temperature intensity covariance of region A-B is 0.8, generate a hyperedge connecting region A and region B, the attribute type is temperature, the weight is 0.8, and the output is a weighted hyperedge set. Each hyperedge clearly includes the connected region nodes, attribute types, and weight values. The hyperedge weight directly reflects the parameter correlation intensity. The higher the weight, the higher the rule priority. Through the hyperedge set, the region-interconnection rules are made explicit, providing physical constraints for brightness optimization;

[0090] Formulate brightness adjustment rules according to the hyperedge weights to balance the brightness requirements of each regional node of the LED lighting and output the regional brightness target value.

[0091] Classify the hyperedge weights according to the environmental attribute types, summarize the hyperedge weights of each type of environmental attribute, and generate global attribute weights;

[0092] Specifically, classify the hyperedge weights according to the environmental attribute types. For example, classify all hyperedges belonging to the temperature attribute into the temperature category, and classify hyperedges belonging to the power grid load attribute into the power grid load category;

[0093] Accumulate and sum the hyperedge weight values of each type of environmental attribute. For example, the total hyperedge weight of the temperature category is 2.4, and the total hyperedge weight of the load category is 1.8;

[0094] Normalize the sum of the weights of each environmental attribute after accumulation according to the attribute type so that the sum of the weights of all attribute types is 1;

[0095] Generate global attribute weights. The global attribute weights clearly record the normalized weight values of each type of attribute. For example, the temperature weight is 0.57 and the load weight is 0.43. Through normalization, it is ensured that the weights of different attribute types are comparable, and the weight values of different attribute types directly reflect the global influence of different environmental attributes on the LED brightness decision;

[0096] Perform weighted summation on the global attribute weights and the environmental attributes of each regional node to obtain the regional brightness demand value of each regional node;

[0097] Based on the global attribute weights and the four types of attribute values of light intensity attribute, user density attribute, temperature attribute, and grid load attribute, for each regional node, extract the four types of global attribute weights and perform weighting on the corresponding light intensity attribute, user density attribute, temperature attribute, and grid load attribute to obtain the contribution degrees of the four types of attributes. Add the contribution degrees of the four types of attributes to obtain the regional brightness demand value of the regional node. Each element in the regional brightness demand value corresponds to the regional brightness demand value of a region. The regional brightness demand value comprehensively reflects the brightness demand of each regional node under the influence of different global attributes. The higher the regional brightness demand value, the higher the brightness allocation required for that region;

[0098] Use the hyperedge weight as the cooperation intensity of each regional node and map the regional brightness demand value to a brightness preference value;

[0099] Define the brightness adjustment rule based on the cooperation intensity and the brightness preference value;

[0100] Specifically, the adjustment rule includes two parts: cooperation constraint and preference priority. The cooperation constraint requires that the brightness difference between regional nodes with high cooperation intensity be less than the set intensity threshold. The preference priority requires that regional nodes with high brightness preference values need to satisfy the brightness demand first. The intensity threshold can be set according to the average or median of the cooperation intensity;

[0101] For example, the cooperation intensity of the temperature attribute between regional node A and its adjacent regional node B is 1.4. If the cooperation intensity threshold of the temperature attribute between the two regions is set to 1.0, then the brightness difference between the two regions needs to be limited within 20% of the maximum allowable brightness difference. The brightness preference value of region A is 0.8 and that of region B is 0.6. Then, when adjusting, the brightness demand of region A is preferentially guaranteed;

[0102] Adjust the initial regional brightness demand value according to the brightness adjustment rule and output the regional brightness target value.

[0103] S3. Map the target value of the area brightness to the PWM duty cycle, and perform LED lighting control according to the PWM duty cycle.

[0104] Map the target value of the area brightness to the PWM duty cycle through the linear relationship of LED lighting;

[0105] Specifically, the target value of the area brightness represents the required LED lighting brightness value for each area node. According to the linear relationship between the brightness of the LED lamp and the PWM duty cycle, establish a mapping rule, define the PWM duty cycle range corresponding to the minimum and maximum values of the target value of the area brightness. For example, the lowest brightness of 100 lux corresponds to a PWM duty cycle of 10%, and the highest brightness of 1000 lux corresponds to a PWM duty cycle of 100%. Calculate the specific PWM duty cycle value corresponding to each target value of the area brightness through linear interpolation to ensure a linear positive correlation between the brightness and the PWM duty cycle;

[0106] Send the PWM duty cycle to the LED controller through the SPI protocol;

[0107] Set the PWM period according to the PWM frequency range inside the LED controller;

[0108] Specifically, read the PWM frequency range supported by the LED controller, select the target frequency according to the application scenario requirements. For example, select 1 kHz for the industrial scenario without flicker requirements, set the corresponding PWM period value, and write the period value into the LED controller;

[0109] Based on the PWM period and the PWM duty cycle, calculate the high-level time of the PWM duty cycle to drive the LED brightness control;

[0110] According to the PWM period value and the PWM duty cycle value, calculate the high-level time of the PWM duty cycle. For example, a period of 1000 microseconds and a PWM duty cycle of 50% correspond to a high-level time of 500 microseconds. Write the high-level time value into the high-level time register of the LED controller. The low-level time is automatically calculated as the period minus the high-level time. The LED controller generates a PWM signal based on the PWM period and the value in the high-level time register and outputs it to the LED drive circuit. The drive circuit controls the on and off time of the LED lamp according to the high and low level ratio of the PWM signal to drive the LED brightness control;

[0111] S4. Monitor the execution effect of the LED lighting control through a photoresistor, and perform deviation determination between the execution effect and the target value of the area brightness, and output the determination result.

[0112] Install a photoresistor at the area node to monitor the light intensity of the LED lighting and generate a real-time LED lighting brightness value;

[0113] Specifically, a photoresistor is installed within the LED lighting range of each area node. The installation position of the photoresistor is ensured to match the light source distribution range of the LED lamp. At the central position of the LED lighting range, the photoresistor measures the light intensity of the current area's LED lighting at a fixed sampling frequency. After noise filtering processing, it is stored as the real-time LED lighting brightness value;

[0114] Calculate the deviation between the real-time LED lighting brightness value and the area brightness target value to generate a brightness deviation value;

[0115] For each area node, calculate the deviation value between the real-time brightness and the target brightness through difference operation. The calculation result retains the positive and negative signs of the original value. A positive deviation indicates that the current LED lighting brightness is too high, and a negative deviation indicates that the LED lighting brightness is insufficient;

[0116] Set a brightness deviation threshold and perform a deviation determination between the brightness deviation value and the brightness deviation threshold;

[0117] The brightness deviation threshold is pre-configured according to the tolerance of the application scenario. For example, a dynamic threshold is determined by statistically analyzing the brightness fluctuations in each area over the past 30 days;

[0118] When the brightness deviation value does not exceed the brightness deviation threshold, it is determined that the area brightness target value does not need to be adjusted;

[0119] When the brightness deviation value exceeds the brightness deviation threshold, it is determined that the area brightness target value needs to be adjusted, and the area node is marked;

[0120] Specifically, for the area nodes whose determination result is that no adjustment is needed, the original LED lighting control is maintained. For the area nodes determined to need adjustment, the area nodes where they are located are marked as to be adjusted, and the specific deviation value by which the area node to be adjusted exceeds the brightness deviation threshold and the PWM duty cycle corresponding to the area node are extracted.

[0121] S5. Divide the conflict areas according to the determination result, encode the PWM duty cycles of the conflict areas into quantum entanglement states, and decompose the quantum entanglement states to generate cross-area brightness adjustment rules.

[0122] Summarize the marked area nodes according to the judgment result to generate a conflict area list;

[0123] Extract the PWM duty cycle from the conflict area list;

[0124] Encode the PWM duty cycle into a quantum entanglement state through quantum amplitude encoding and quantum bit entanglement gate;

[0125] Specifically, perform a normalization operation on the PWM duty cycle extracted from the conflict area list. For example, convert 50% to 0.5, and encode the normalized PWM duty cycle as a single qubit state through quantum amplitude encoding. For area nodes with spatial or functional correlations (such as adjacent bedrooms and corridors), apply a quantum entanglement gate to perform an entanglement operation on the single qubit state to generate a quantum entanglement state;

[0126] Decompose the quantum entanglement state through quantum principal component analysis to generate the correlation strength of the area nodes. According to the correlation strength, adjust the LED lighting brightness across regions.

[0127] Perform quantum principal component analysis on the quantum entanglement state, and extract the principal components through the quantum phase estimation algorithm. For example, the principal component of the quantum entanglement state of area nodes A - B shows that its correlation weight accounts for 70%, which characterizes the strong collaborative demand for brightness adjustment between the two regions. The strong collaborative demand is the correlation strength of the area nodes;

[0128] Generate a cross - region adjustment strategy based on the correlation strength. The greater the correlation strength, the greater the connection between the area nodes. The correlation strength value determines the allowable brightness difference.

[0129] This embodiment also provides an LED lighting intelligent control system based on multi - condition decision - making, including:

[0130] An acquisition module that acquires environmental data and performs pre - processing, and converts the environmental data into a four - dimensional quantum state tensor through quantum feature mapping. The environmental data includes area data, illumination data, user density data, temperature data, and power grid load data;

[0131] A brightness module that analyzes each item of environmental data in the four - dimensional quantum state tensor, defines a hyper - edge connection strategy, adjusts the LED lighting demand according to the hyper - edge connection strategy, and generates a regional brightness target value;

[0132] An execution module that maps the regional brightness target value to a PWM duty cycle and performs LED lighting control according to the PWM duty cycle;

[0133] A determination module that monitors the execution effect of the LED lighting control through a photoresistor and performs a deviation determination between the execution effect and the regional brightness target value, and outputs a determination result;

[0134] An adjustment module that divides the conflict areas according to the determination result, encodes the PWM duty cycle of the conflict areas as a quantum entanglement state, and decomposes the quantum entanglement state to generate a cross - region brightness adjustment rule.

[0135] This embodiment also provides a computer device, which is applicable to the case of the intelligent control method of LED lighting based on multi-condition decision-making, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the intelligent control method of LED lighting based on multi-condition decision-making as proposed in the above embodiment.

[0136] The computer device can be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the outer shell of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0137] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the intelligent control method of LED lighting based on multi-condition decision-making as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0138] In summary, the present invention defines a hyperedge connection strategy by analyzing environmental data, significantly improving the accuracy of the regional brightness target value. Based on the four-dimensional quantum state tensor, hyperedges are generated through the intensity covariance of the environmental attributes of regional nodes to quantify the synergy intensity of multi-attribute superposition. Utilizing the expression ability of hypergraphs for multi-node high-order relationships, it breaks through the limitation of the traditional adjacency matrix for binary linear correlations, realizes the dynamic weight allocation of multi-environmental attributes across regions, and thus generates a regional brightness target value that takes into account local requirements and global energy consumption balance. By combining the quantization data basis with the hypergraph cooperation rules, a core framework for multi-condition decision-making is constructed, providing an accurate initial decision basis for closed-loop dimming and conflict optimization.

[0139] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. An intelligent control method for LED lighting based on multi - condition decision, characterized in that: including, collecting environmental data and preprocessing it, and converting the environmental data into a four-dimensional quantum state tensor through quantum feature mapping, where the environmental data includes area data, illumination data, user density data, temperature data, and grid load data; analyzing each item of environmental data in the four-dimensional quantum state tensor, defining a hyperedge connection strategy, adjusting the LED lighting demand according to the hyperedge connection strategy, and generating a regional brightness target value; mapping the regional brightness target value to a PWM duty cycle, and performing LED lighting control according to the PWM duty cycle; monitoring the execution effect of the LED lighting control through a photoresistor, and making a deviation determination between the execution effect and the regional brightness target value, and outputting a determination result; dividing conflict areas according to the determination result, encoding the PWM duty cycle of the conflict areas into a quantum entanglement state, and decomposing the quantum entanglement state to generate cross-regional brightness adjustment rules.

2. The intelligent control method for LED lighting based on multi-condition decision according to claim 1, characterized in that: The specific steps for converting environmental data into a four-dimensional quantum state tensor through quantum feature mapping are as follows. Regarding the preprocessed environmental data as an independent one-dimensional data sequence; extracting the environmental parameter values of the illumination data, user density data, temperature data, and grid load data in the one-dimensional data sequence through data indexing; using quantum amplitude encoding to map the environmental parameter values to a one-dimensional quantum state sequence; aggregating multiple one-dimensional quantum state sequences through tensor product to generate a four-dimensional quantum state tensor.

3. The intelligent control method for LED lighting based on multi-condition decision according to claim 2, characterized in that: The specific steps for analyzing each item of environmental data in the four-dimensional quantum state tensor and defining a hyperedge connection strategy are as follows. classifying the four-dimensional quantum state tensor according to the area boundary in the area data to generate functional areas; defining each functional area as a regional node of a hypergraph; regarding the illumination data, user density data, temperature data, and grid load data as the environmental attributes of the hypergraph regional nodes; pairing the regional nodes with the neighboring regional nodes to generate a region-neighborhood node group, and calculating the intensity covariance of each environmental attribute of the region-neighborhood node group; setting an intensity covariance threshold, and judging whether the intensity covariance is greater than the intensity covariance threshold; if the intensity covariance is greater than the intensity covariance threshold, regarding the region-neighborhood node group as a hyperedge, and taking the intensity covariance value as the hyperedge weight.

4. The intelligent control method for LED lighting based on multi-condition decision according to claim 3, characterized in that: The specific steps for adjusting the LED lighting demand according to the hyperedge connection strategy and generating a regional brightness target value are as follows. classifying the hyperedge weights according to the environmental attribute types, and summarizing the hyperedge weights of each type of environmental attribute to generate global attribute weights; performing weighted summation on the global attribute weights and the environmental attributes of each regional node to obtain the regional brightness demand values of each regional node; taking the hyperedge weights as the cooperation intensity of each regional node, and mapping the regional brightness demand value to a brightness tendency value; defining a brightness adjustment rule based on the cooperation intensity and the brightness tendency value; adjusting the initial regional brightness demand value according to the brightness adjustment rule, and outputting the regional brightness target value.

5. The intelligent control method for LED lighting based on multi-condition decision according to claim 4, characterized in that: The specific steps for mapping the regional brightness target value to a PWM duty cycle and performing LED lighting control according to the PWM duty cycle are as follows. mapping the regional brightness target value to a PWM duty cycle through the linear relationship of LED lighting; sending the PWM duty cycle to the LED controller through the SPI protocol; Set the PWM period according to the PWM frequency range inside the LED controller; Based on the PWM period and the PWM duty cycle, calculate the high-level time of the PWM duty cycle to drive the LED brightness control.

6. The intelligent control method for LED lighting based on multi-condition decision according to claim 5, characterized in that: Monitor the execution effect of the LED lighting control through a photoresistor, and make a deviation determination between the execution effect and the regional brightness target value, and output the determination result. The specific steps are as follows: Monitor the light intensity of the LED lighting to generate a real-time LED lighting brightness value; Calculate the deviation between the real-time LED lighting brightness value and the regional brightness target value to generate a brightness deviation value; Set a brightness deviation threshold, and make a deviation determination between the brightness deviation value and the brightness deviation threshold; When the brightness deviation value does not exceed the brightness deviation threshold, it is determined that the regional brightness target value does not need to be adjusted; When the brightness deviation value exceeds the brightness deviation threshold, it is determined that the regional brightness target value needs to be adjusted, and the regional node is marked.

7. The intelligent control method for LED lighting based on multi-condition decision according to claim 6, characterized in that: Divide the conflict area according to the determination result, encode the PWM duty cycle of the conflict area into a quantum entanglement state, and decompose the quantum entanglement state to generate a cross-regional brightness adjustment rule. The specific steps are as follows: Summarize the marked regional nodes according to the judgment result to generate a conflict area list; Extract the PWM duty cycle from the conflict area list; Encode the PWM duty cycle into a quantum entanglement state through quantum amplitude encoding and quantum qubit entanglement gate; Decompose the quantum entanglement state through quantum principal component analysis to generate the correlation strength of the regional nodes, and adjust the LED lighting brightness across regions according to the correlation strength.

8. An LED lighting intelligent control system based on multi-condition decision-making, based on the multi-condition decision-making LED lighting intelligent control method according to any one of claims 1 to 7, characterized in that: Including: An acquisition module that acquires environmental data and performs preprocessing, and converts the environmental data into a four-dimensional quantum state tensor through quantum feature mapping. The environmental data includes regional data, light data, user density data, temperature data, and grid load data; A brightness module that analyzes each item of environmental data in the four-dimensional quantum state tensor, defines a hyperedge connection strategy, adjusts the LED lighting demand according to the hyperedge connection strategy, and generates a regional brightness target value; An execution module that maps the regional brightness target value to a PWM duty cycle and executes LED lighting control according to the PWM duty cycle; A determination module that monitors the execution effect of the LED lighting control through a photoresistor, and makes a deviation determination between the execution effect and the regional brightness target value, and outputs the determination result; An adjustment module that divides the conflict area according to the determination result, encodes the PWM duty cycle of the conflict area into a quantum entanglement state, and decomposes the quantum entanglement state to generate a cross-regional brightness adjustment rule.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the LED lighting intelligent control method based on multi-condition decision-making according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the LED lighting intelligent control method based on multi-condition decision-making according to any one of claims 1 to 7.

Images