Task processing capability optimization method for intelligent lighting system and related equipment

Abstract

The embodiment of the invention belongs to the technical field of computers, and relates to a task processing capability optimization method for an intelligent lighting system, which comprises the following steps: acquiring historical user data of the intelligent lighting system to be optimized; calculating the historical user data according to a preset similarity calculation model to obtain user behavior similarity; predicting the user behavior similarity according to a preset behavior prediction model to obtain user demand information; and according to the user demand information, generating a target intelligent illumination scheme and controlling the intelligent illumination system to execute the intelligent illumination scheme. The invention further provides a task processing capability optimization device for the intelligent lighting system, computer equipment and a storage medium. In addition, the invention also relates to a block chain technology, and the historical user data, the user behavior similarity and the user demand information can be stored in a block chain. The intelligent and personalized levels of the system are improved, and the user experience and the operation efficiency and task processing capacity of the system are improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method for optimizing task processing capabilities of an intelligent lighting system and related equipment. Background Art

[0002] Smart lighting systems typically employ rule-based control, controlling lighting devices on and off, dimming them, and so on, according to pre-set rules. To enhance the system's intelligence, some systems also employ machine learning algorithms to learn user behaviors, more accurately predicting their needs and providing personalized lighting services. Furthermore, some systems employ big data analytics to compile statistics and analyze user lighting needs, thereby optimizing lighting strategies.

[0003] However, in practical applications, the rule-based control methods used by current intelligent lighting systems often cannot adapt to complex environments and user needs, resulting in poor task processing capabilities of intelligent lighting systems and a poor user experience. Summary of the Invention

[0004] The purpose of the embodiments of the present application is to provide a method and related equipment for optimizing the task processing capability of an intelligent lighting system, so as to solve the technical problem of poor task processing capability of the intelligent lighting system.

[0005] To solve the above technical problems, the present invention provides a method for optimizing the task processing capability of an intelligent lighting system, which adopts the following technical solutions:

[0006] A method for optimizing task processing capability of an intelligent lighting system comprises the following steps:

[0007] Obtain historical user data of the smart lighting system to be optimized;

[0008] Calculating the historical user data according to a preset similarity calculation model to obtain user behavior similarity;

[0009] Predicting the user behavior similarity based on a preset behavior prediction model to obtain user demand information;

[0010] According to the user demand information, a target intelligent lighting solution is generated and the intelligent lighting system is controlled to execute the intelligent lighting solution.

[0011] Furthermore, before the step of calculating the historical user data according to the preset similarity calculation model to obtain the user behavior similarity, the method further includes:

[0012] Obtain user behavior data related to smart lighting;

[0013] Preprocessing the user behavior data to obtain a feature data set;

[0014] Constructing the similarity calculation model according to the feature data set and a preset first deep learning algorithm;

[0015] The behavior prediction model is constructed based on the feature data set and a preset second deep learning algorithm.

[0016] Furthermore, the first deep learning algorithm includes a convolutional neural network algorithm, and the step of constructing the similarity calculation model based on the feature data set and the preset first deep learning algorithm specifically includes:

[0017] Performing data segmentation on the feature data set to obtain a first training set and a first test set;

[0018] Establishing a first initial model by the convolutional neural network algorithm;

[0019] Performing model training on the first initial model according to the first training set to obtain a trained first target model;

[0020] The first target model is optimized according to the first test set to obtain the similarity calculation model.

[0021] Furthermore, the second deep learning algorithm includes an adaptive learning algorithm, and the step of constructing the behavior prediction model based on the feature data set and the preset second deep learning algorithm specifically includes:

[0022] Performing data segmentation on the feature data set to obtain a second training set and a second test set;

[0023] Establishing a second initial model by the adaptive learning algorithm;

[0024] Performing model training on the second initial model according to the second training set to obtain a trained second target model;

[0025] The second target model is optimized according to the second test set to obtain the behavior prediction model.

[0026] Furthermore, the step of preprocessing the user behavior data to obtain a feature data set specifically includes:

[0027] Performing data cleaning, data integration, data transformation, and data reduction on the user behavior data to obtain data to be extracted;

[0028] Feature extraction is performed on the data to be extracted to obtain the feature data set.

[0029] Furthermore, the similarity calculation model and the behavior prediction model adopt a distributed computing framework, the similarity calculation model processes the historical user data in parallel through multiple computing nodes, and the behavior prediction model processes the user behavior similarity in parallel through multiple computing nodes.

[0030] Furthermore, after the step of generating a target intelligent lighting solution according to the user demand information and controlling the intelligent lighting system to execute the intelligent lighting solution, the method further includes:

[0031] The historical user data, the user behavior similarity and the user demand information are stored in a preset blockchain node.

[0032] In order to solve the above technical problems, the embodiment of the present application further provides a task processing capability optimization device for an intelligent lighting system, which adopts the following technical solution:

[0033] A task processing capability optimization device for an intelligent lighting system, comprising:

[0034] An acquisition module, used to acquire historical user data of the intelligent lighting system to be optimized;

[0035] A calculation module, configured to calculate the historical user data according to a preset similarity calculation model to obtain user behavior similarity;

[0036] A prediction module is used to predict the user behavior similarity based on a preset behavior prediction model to obtain user demand information;

[0037] A generation module is used to generate a target intelligent lighting solution according to the user demand information and control the intelligent lighting system to execute the intelligent lighting solution.

[0038] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0039] A computer device includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the task processing capability optimization method for an intelligent lighting system are implemented as described above.

[0040] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0041] A computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the above-mentioned method for optimizing task processing capability of an intelligent lighting system.

[0042] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0043] The method for optimizing the task processing capacity of an intelligent lighting system disclosed in this application obtains historical user data of the intelligent lighting system to be optimized; calculates the historical user data according to a preset similarity calculation model to obtain user behavior similarity; predicts the user behavior similarity according to a preset behavior prediction model to obtain user demand information; and generates a target intelligent lighting solution based on the user demand information and controls the intelligent lighting system to execute the intelligent lighting solution. By obtaining historical user data and processing the data using a similarity calculation model to predict user demand and generate a target intelligent lighting solution, the application enables the intelligent lighting system to dynamically adjust lighting strategies based on the user's actual behavior, thereby improving the system's intelligence and personalization, avoiding the limitations of traditional rule-based control methods, and enhancing the user experience, system operating efficiency, and task processing capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the solutions in this application, a brief introduction will be given below to the drawings required for use in the description of the embodiments of this application. Obviously, the drawings described below are some embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0045] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0046] Figure 2 is a flowchart of an embodiment of a method for optimizing task processing capability of an intelligent lighting system according to the present application;

[0047] Figure 3 is a structural diagram of an embodiment of a task processing capability optimization device for an intelligent lighting system according to the present application;

[0048] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0050] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0051] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0052] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. Network 104 is a medium for providing communication links between terminal devices 101, 102, 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0053] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0054] Terminal devices 101, 102, and 103 can be various electronic devices with display screens and support web browsing, including but not limited to smartphones, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, and the like.

[0055] The server 105 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal devices 101 , 102 , and 103 .

[0056] It should be noted that the task processing capability optimization method for the intelligent lighting system provided in the embodiment of the present application is generally executed by a terminal device. Accordingly, the task processing capability optimization device for the intelligent lighting system is generally provided in the terminal device.

[0057] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0058] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for optimizing task processing capability of an intelligent lighting system according to the present application. The method for optimizing task processing capability of an intelligent lighting system comprises the following steps:

[0059] Step S201: Acquire historical user data of the smart lighting system to be optimized.

[0060] In this embodiment, the task processing capability optimization method for the intelligent lighting system is run on the electronic device (eg Figure 1 The terminal device shown in the figure can send or receive data via a wired connection or a wireless connection. It should be noted that the above-mentioned wireless connection methods may include but are not limited to 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (ultra wideband) connections, and other wireless connection methods currently known or to be developed in the future.

[0061] In this embodiment, the purpose of this step is to collect and store historical behavioral data for all users in the system. This historical data may include information such as users' lighting usage patterns, activity times, locations, frequency, and lighting preferences. The system can collect this data through sensors, cameras, smart home devices, and other means, and store it in a database. Data collection typically involves the integration of IoT technology and sensing devices. For example, if a smart lighting system is installed in an office, user behavioral data may include turning lights on and off at different time periods, brightness requirements in different scenarios (such as meetings and rest periods), and whether there is a preference for automatic lighting adjustment. The system stores this behavioral data in the database for subsequent analysis and optimization. In addition to historical behavioral data, other relevant data can also be collected, such as environmental data (temperature, humidity, light intensity, etc.) and user physiological data (such as activity intensity and heart rate) to provide more precise and personalized services.

[0062] Step S202 : Calculate the historical user data according to a preset similarity calculation model to obtain user behavior similarity.

[0063] In this embodiment, the similarity of behaviors between different users is analyzed through a similarity calculation model (such as cosine similarity, Jacquard similarity, or embedded representation based on deep learning). The model calculates the similarity of user behaviors based on the collected historical user data. Suppose user A and user B work in the same office. User A turns on the lights at 9 o'clock every day and maintains a certain brightness until leaving at 6 o'clock in the afternoon, while user B turns on the lights at 7 o'clock, and the brightness of the lights is adjusted to be brighter during the noon period. Through the similarity calculation model, the system can find certain similarities between user A and user B in time and brightness, even though their behavior patterns are slightly different. More advanced algorithms, such as convolutional neural networks (CNN) or recurrent neural networks (RNN) based on deep learning, can be used to model behavioral data to further improve the accuracy of similarity calculation.

[0064] Step S203: predicting the user behavior similarity according to a preset behavior prediction model to obtain user demand information.

[0065] In this embodiment, at this stage, based on the calculated similarity of user behavior, a behavior prediction model (such as regression analysis, decision tree, neural network, etc.) is used to predict the user's future needs. The model makes inferences based on similar behaviors in historical data and infers the user's lighting needs in a specific environment or time period. The system finds that the behavior similarity between user A and user B is high, so it can be predicted that user B's lighting needs in a certain time period may be similar to those of user A. Based on historical data, the system can infer that user B may also need similar light intensity and timer settings as user A in the next working day. If a large amount of user data is involved, collaborative filtering (such as collaborative filtering based on users or items) can be used to predict individual needs based on group behavior. In addition, the time series prediction model in deep learning (such as LSTM) can be combined to enhance the accuracy of predicting future needs.

[0066] Step S204: generating a target intelligent lighting solution according to the user demand information and controlling the intelligent lighting system to execute the intelligent lighting solution.

[0067] In this embodiment, based on the predicted user demand information, the system generates a corresponding intelligent lighting control plan. This plan includes control instructions such as the lighting device's on / off status, brightness adjustment, and color temperature, and transmits it to the actual lighting device for execution. The intelligent lighting system can be a standalone device or a multi-device system networked with other intelligent devices. Suppose the system determines, based on the user behavior prediction model, that user B needs to keep the lights low between 1:00 PM and 3:00 PM and automatically turn off the lights at 8:00 PM. The system will automatically adjust the lighting device settings based on these predictions without manual user intervention. If the system detects a change in user behavior (for example, user B's activity pattern changes), the preset plan can be modified through an adaptive adjustment mechanism to optimize the control instructions of the intelligent lighting system in real time. A feedback mechanism can be introduced to allow users to evaluate the lighting plan and further adjust the prediction model.

[0068] This application obtains historical user data and processes the data using a similarity calculation model to predict user needs and generate target intelligent lighting solutions. It enables the intelligent lighting system to dynamically adjust lighting strategies based on the user's actual behavior, thereby improving the intelligence and personalization of the system, avoiding the limitations of traditional rule-based control methods, and enhancing user experience and the system's operating efficiency and task processing capabilities.

[0069] In some optional implementations of this embodiment, before the step of calculating the historical user data according to the preset similarity calculation model to obtain the user behavior similarity, the following steps are further included:

[0070] Obtain user behavior data related to smart lighting;

[0071] Preprocessing the user behavior data to obtain a feature data set;

[0072] Constructing the similarity calculation model according to the feature data set and a preset first deep learning algorithm;

[0073] The behavior prediction model is constructed based on the feature data set and a preset second deep learning algorithm.

[0074] In this embodiment, before executing the similarity calculation model, the system first needs to collect user behavior data related to smart lighting. This data includes specific user behaviors when using the smart lighting system, such as lighting on / off status, brightness adjustment, usage scenarios (e.g., work, rest, entertainment), and user activity patterns during different time periods. The smart lighting system can collect user behavior data in real time through various sensors (e.g., motion sensors and light sensors). For example, suppose a user turns on the lights at 8:00 AM every day, adjusts the brightness to a specific value, and turns off the lights at 6:00 PM. This behavior data will become the raw data collected by the system. In addition to basic behavioral data, the system can also collect data related to user preferences, such as manual settings and voice control operation records, to further enrich the dimensionality of user behavior data. After collection, user behavior data typically undergoes preprocessing to extract meaningful features. These features can effectively assist in constructing similarity calculation and behavior prediction models. This preprocessing process can include data cleaning, noise removal, missing value filling, and normalization or standardization. Assuming that the collected user behavior data contains missing light intensity data for certain time periods, the preprocessing step will interpolate and fill in these missing values. The system may also normalize the behavior data of different users so that they are all on the same scale, minimizing the impact of varying data scales on model training. The preprocessing step may also include time-series processing of the data. For example, this can be done by dividing the user behavior data into time windows, processing the behavioral features within each time window, and constructing a separate feature dataset for each time window. Based on this preprocessed feature dataset, the system uses a deep learning algorithm to construct a similarity calculation model. The goal of this similarity calculation model is to identify user groups with similar needs by evaluating the similarities between different user behaviors. Deep learning algorithms, such as convolutional neural networks (CNNs) or autoencoders, can learn deep patterns from user lighting behaviors and calculate similarity between users. For example, if user A and user B have very similar lighting patterns and brightness settings over multiple time periods, the deep learning model can identify this similarity and provide similar lighting services to these two users. In addition to common deep learning models, other types of neural networks, such as long short-term memory networks (LSTMs) or graph neural networks (GNNs), can also be used. These models are particularly useful when processing time series data or data with complex dependencies. These models can capture both long-term and short-term patterns in user behavior. The system uses another deep learning algorithm to build a behavior prediction model based on the feature dataset. The purpose of the behavior prediction model is to predict the user's future lighting needs, such as when the user needs to adjust the lighting brightness or turn off the lights.Suppose the system uses a recurrent neural network (RNN) or long short-term memory network (LSTM) based on user A's historical data to predict the user's lighting needs over the next few hours or days. Based on this prediction, the system can adjust the lighting in advance to improve energy efficiency or comfort. Behavior prediction models can also be combined with reinforcement learning algorithms to make more complex decisions. For example, using Q-learning or deep Q-networks (DQNs) to predict user behavior. By learning from user feedback, the system can adjust its prediction strategy in real time, improving both accuracy and flexibility.

[0075] This application preprocesses the data and extracts an effective feature data set, providing high-quality input data for subsequent similarity calculation and behavior prediction, further improving the prediction accuracy of the model.

[0076] In some optional implementations of this embodiment, the first deep learning algorithm includes a convolutional neural network algorithm, and the step of constructing the similarity calculation model based on the feature data set and the preset first deep learning algorithm specifically includes:

[0077] Performing data segmentation on the feature data set to obtain a first training set and a first test set;

[0078] Establishing a first initial model by the convolutional neural network algorithm;

[0079] Performing model training on the first initial model according to the first training set to obtain a trained first target model;

[0080] The first target model is optimized according to the first test set to obtain the similarity calculation model.

[0081] In this embodiment, when using a convolutional neural network (CNN) algorithm to construct a similarity calculation model, the feature dataset must first be divided into two subsets: a first training set and a first test set. The first training set is used to train the model so that it can learn patterns in the data; the first test set is used to evaluate the performance of the trained model to ensure that the model has good generalization capabilities. Assuming that the user behavior dataset collected by the system contains 1,000 samples, this data can be divided into 800 training samples and 200 test samples in an 80:20 ratio. During the training process, the CNN model will use the 800 training samples for learning, while the 200 test samples are used to test the model's predictive ability. In addition to the traditional training set and test set division method, cross-validation technology can also be used. Especially when the data volume is small, cross-validation ensures that the model evaluation is more stable and reliable by splitting the dataset multiple times. After the data segmentation is completed, the first initial model is established using the convolutional neural network (CNN) algorithm. Convolutional neural networks are a deep learning algorithm that is particularly good at processing data with local correlation structures (such as image data, time series data, etc.). The CNN model is used to extract local features from user behavior data and construct a similarity calculation model. Assuming that user behavior data includes multiple features, such as activity time and brightness settings, the CNN algorithm extracts these local features through a series of convolutional layers. For example, the model might discover that users typically have similar brightness settings during a specific time period, or that users exhibit very similar behavior patterns in certain scenarios. While convolutional neural networks are the core algorithm in this technical solution, other algorithms can also be used to construct the initial model. For example, autoencoders can be used for dimensionality reduction and feature extraction, and can also serve as the initial construction method for the similarity calculation model. Next, the system trains the model by inputting the training set into the convolutional neural network. The goal of the training process is to optimize the network parameters (such as the convolution kernel and weights) so that the model can accurately learn features from the input data and effectively perform similarity calculations. During the model training process, the convolutional neural network adjusts the weights and parameters using a backpropagation algorithm to reduce prediction error. For example, if the system mistakenly classifies the behavior data of certain users in the training set as dissimilar, the CNN model will adjust its weights during training to reduce the occurrence of such errors. In addition to using traditional training sets for model training, you can also use transfer learning techniques to accelerate the training process of the target model by migrating existing pre-trained models. Transfer learning can help solve the problem of insufficient data. Especially for complex tasks, fine-tuning using pre-trained models can improve model training efficiency.After training is completed, the system uses the test set to evaluate the performance of the target model and optimize the model. By comparing the prediction results of the test set with the true labels (actual user behavior data), the performance of the model (such as accuracy, precision, recall, etc.) will be calculated. If the model performs poorly, the optimization step will further adjust the model parameters. Assuming that the prediction results of the target model on the test set show that the similarity prediction of certain user behaviors is inaccurate, resulting in the generation of incorrect lighting plans, the optimization step will improve the model's ability to predict similarity by adjusting the parameters of the CNN. Optimization methods may include adjusting the learning rate, increasing the training cycle, or using more complex optimization algorithms (such as the Adam optimizer). To further improve the optimization effect, regularization methods can be introduced, such as L2 regularization (weight decay) to reduce overfitting, or using Dropout technology to randomly discard neurons to prevent the model from relying on certain specific features.

[0082] This application uses deep learning algorithms such as convolutional neural networks (CNN) to perform similarity calculations, which can more accurately explore the potential patterns and regularities in user behavior; through data segmentation and training optimization, an efficient similarity calculation model can be obtained, enabling the system to better identify and predict user behavior, provide personalized lighting control, and improve the accuracy and response speed of the intelligent lighting system.

[0083] In some optional implementations of this embodiment, the second deep learning algorithm includes an adaptive learning algorithm, and the step of constructing the behavior prediction model based on the feature data set and the preset second deep learning algorithm specifically includes:

[0084] Performing data segmentation on the feature data set to obtain a second training set and a second test set;

[0085] Establishing a second initial model by the adaptive learning algorithm;

[0086] Performing model training on the second initial model according to the second training set to obtain a trained second target model;

[0087] The second target model is optimized according to the second test set to obtain the behavior prediction model.

[0088] In this embodiment, similar to the data segmentation step described above, the feature dataset is further segmented to construct a behavior prediction model. The purpose of data segmentation is to divide the data into a second training set and a second test set to ensure that the model can learn effective patterns during training and evaluate its generalization ability through the test set. Assume that user behavior data contains multiple dimensions, such as activity type, time, environmental conditions, etc. By splitting the dataset into an 80% second training set (e.g., 2000 data items) and a 20% second test set (e.g., 500 data items), overfitting can be effectively avoided and the model's generalization ability can be improved. In addition to traditional training set and test set segmentation methods, k-fold cross-validation can be used to further improve the accuracy of model evaluation. In k-fold cross-validation, the dataset is divided into k subsets, and the model is validated using a method that uses k-1 subsets for training and 1 subset for testing each time. The final model performance is determined by the results of multiple validations. After data segmentation is completed, an initial version of the behavior prediction model is constructed using an adaptive learning algorithm. Adaptive learning algorithms are a type of algorithm that can automatically adjust learning strategies based on input data. Common adaptive learning algorithms include reinforcement learning and online learning. Adaptive learning algorithms can adjust model parameters in real time based on changing environmental or data characteristics during training, thereby improving prediction accuracy and real-time performance. For example, using the Q-learning algorithm as an adaptive learning algorithm, the system adapts to different user behavior patterns during training through real-time feedback, allowing the model to continuously optimize its predictions as user behavior data gradually changes. If an online learning algorithm is used, Stochastic Gradient Descent (SGD) can be chosen as an adaptive learning method. By updating the model weights online, the model can quickly adapt to changes in user needs. The second initial model is trained using a second training set. The goal is to optimize the model parameters through repeated training on the data, enabling it to accurately predict user needs. The adaptive learning algorithm gradually adjusts the weights and biases based on the data from the second training set. During training, if the model predicts a user's behavior but significantly differs from the actual needs, the model uses backpropagation to adjust its parameters to reduce the error. In the case of reinforcement learning algorithms, model training is performed through feedback rewards (for accurate behavior predictions) and penalties (for incorrect predictions). For more complex cases, transfer learning techniques can be used to fine-tune existing trained models. Especially when the target task and the source task are similar, transfer learning can improve training efficiency and reduce the need for large amounts of data.Finally, the trained second target model is optimized to ensure that it can adapt to the needs of different user behaviors. The test set is used to evaluate the effect of the target model. The optimization step adjusts the model parameters to make the model's performance more accurate and reliable, avoiding overfitting or underfitting. If the performance of the second target model on the test set is not ideal, the optimization step will further improve the accuracy of the model by adjusting hyperparameters (such as learning rate, model structure, etc.) or increasing the training set data. For example, if the test set shows inaccurate predictions, it may be that the model has not fully learned certain important patterns in user behavior. In this case, the optimization step may include adding deep learning network layers or introducing additional features. During the optimization process, ensemble learning methods such as random forests or XGBoost can also be used to further improve the accuracy and stability of the model by combining the prediction results of multiple models. Ensemble learning can reduce the overfitting problem that may occur in a single model.

[0089] Through continuous learning and adjustment, the system can still provide accurate prediction results with limited training data, reduce computational complexity, improve the real-time application capability of the algorithm, and adapt to rapidly changing user needs.

[0090] In some optional implementations of this embodiment, the step of preprocessing the user behavior data to obtain a feature data set specifically includes:

[0091] Performing data cleaning, data integration, data transformation, and data reduction on the user behavior data to obtain data to be extracted;

[0092] Feature extraction is performed on the data to be extracted to obtain the feature data set.

[0093] In this embodiment, in the preprocessing step, user behavior data first needs to undergo multiple stages of processing to ensure data quality and usability. These processing steps can ensure that the data input to the model is more standardized and useful, improving the effectiveness of subsequent analysis and model training. Data cleaning refers to removing or repairing errors, missing values, and outliers in the data. For example, user behavior data may contain missing timestamps or incomplete records of certain behaviors. Data cleaning ensures data accuracy by filling missing values ​​and removing inconsistent data. Data integration integrates multiple data from different sources. For example, a smart lighting system may involve sensor data, user activity data, and environmental data (such as light intensity and temperature). Data integration ensures that these data can be processed uniformly to eliminate the impact of source differences. Data transformation converts data into a format suitable for subsequent analysis. For example, timestamps may need to be converted to periodic features (such as hours, days of the week, etc.), or certain numerical features need to be normalized so that the data can be compared on the same scale. Data reduction reduces the dimensionality or size of the dataset while retaining the key features of the data. Techniques such as feature selection and principal component analysis (PCA) can be used to reduce data complexity, reduce redundancy, and improve computational efficiency. Suppose a smart lighting system collects information such as user dwell time in different rooms, light on / off operations, indoor temperature, and humidity. Data cleaning can remove missing or invalid records. Data integration can combine data from different sensors into a unified dataset. Data transformation can convert user dwell time into hourly behavioral patterns. Finally, data reduction can condense user behavioral patterns into a set of key time-period features. Furthermore, anomaly detection techniques can be applied during the data cleaning phase to improve data quality by identifying and removing data that deviates from normal patterns. Feature extraction involves filtering out features that are important for the target task from the data to be extracted, while removing irrelevant or redundant components. Feature extraction can improve model efficiency and performance. This step converts the data into an input format that can be processed by a machine learning model, and extracts key features that represent user behavior. Feature extraction algorithms and methods can be selected based on the specific problem. For example, based on user behavior data, behavioral features such as average dwell time in different time periods, most frequently used rooms, and light on / off frequency can be extracted. Deep learning methods (such as convolutional neural networks) can also automatically extract effective features from complex raw data.Assuming the collected data includes user dwell time in different rooms, light intensity, and motion sensor feedback, feature extraction can be used to extract user behavior patterns within specific time periods, such as the total dwell time between 8:00 and 9:00 a.m., and whether there are special lighting requirements (such as energy-saving mode). These extracted features will be passed as input to subsequent models for prediction and optimization. During the feature extraction process, natural language processing technology can also be introduced to process text data in user behavior logs, such as analyzing user feedback or voice control commands in mobile apps. Using NLP technology, relevant information about user needs and preferences can be extracted from text to serve as features for predicting lighting system behavior.

[0094] Through feature extraction, this application enables the system to extract information valuable for prediction, build a more accurate feature data set, provide efficient data support for similarity calculation and behavior prediction, and improve the accuracy of prediction and the intelligence level of the system.

[0095] In some optional implementations of this embodiment, the above-mentioned similarity calculation model and the behavior prediction model adopt a distributed computing framework, the similarity calculation model processes the historical user data in parallel through multiple computing nodes, and the behavior prediction model processes the user behavior similarity in parallel through multiple computing nodes.

[0096] In this embodiment, the distributed computing framework refers to distributing computing tasks to multiple computing nodes (for example, servers, virtual machines, containers, etc.) for parallel processing. Through distributed computing, computing efficiency can be greatly improved, especially for the processing of large-scale data, avoiding the performance bottleneck of a single computing node. When calculating the similarity of user behavior data in the similarity calculation model, the amount of data is usually large. By adopting a distributed computing framework, the data can be divided and distributed to different computing nodes for parallel computing, thereby improving the speed and efficiency of similarity calculation. In this way, even if the data set is huge, the system can still perform similarity calculation efficiently and adapt to the needs of real-time data stream processing. The behavior prediction model can also accelerate the prediction process through a distributed computing framework. In the behavior prediction stage, the model needs to infer and process a large amount of user behavior data. Through distributed computing, the data can be divided into multiple subsets, each subset is predicted by a different computing node, and finally merged to obtain the result, thereby reducing the overall computing time. In a smart city, the lighting system needs to process massive amounts of data from various buildings, rooms, and sensors. Distributed computing allows this data to be partitioned by location and time. User behavior similarity is calculated on different compute nodes, and lighting demand forecasts are then generated. The results from each node are then aggregated. Similarity calculation models aim to assess the similarity between different user behaviors based on historical user data. Parallel computing allows historical data to be partitioned into multiple subsets, each of which can be processed independently, reducing computational time. Each compute node processes a portion of the historical data, enabling rapid calculation of the similarity between individual user behaviors. During data partitioning and distribution, user behavior data can be partitioned by time, region, or user group. Each compute node receives a portion of the data and performs similarity calculations. Multiple compute nodes can perform similarity calculations between different users in parallel, and the results are aggregated upon completion. Typical distributed computing frameworks automatically assign computational tasks to individual compute nodes for processing, ultimately merging the results from each node to produce the final global similarity result. In the intelligent lighting system of a large commercial building, multiple users turn lights on and off at different times. The system divides user behavior data into multiple small blocks through a distributed computing framework and calculates user behavior similarities in parallel on multiple computing nodes. Ultimately, the system adjusts the lighting settings to meet user needs based on the calculated similarities. In the behavior prediction model stage, the system predicts users' future needs based on the calculated user behavior similarities. To speed up the prediction process, the system uses multiple computing nodes to process similarity data in parallel and execute prediction tasks on different nodes. User behavior prediction usually involves large amounts of data processing and complex computing models. In a distributed environment, the data will be divided into multiple small blocks. Each computing node processes a portion of the similarity data, independently performs the behavior prediction task, and aggregates the results, thereby accelerating the prediction process.Distributed computing frameworks typically include load balancing capabilities, dynamically adjusting task allocation across compute nodes to ensure balanced load across all nodes and avoid performance bottlenecks caused by overloading certain nodes. When the system needs to predict the lighting needs of multiple users in different scenarios, the distributed computing framework divides historical similarity data by scenario and user, assigning it to multiple compute nodes for processing. These nodes perform parallel computations and predictions on user needs, ultimately aggregating the results to optimize the system's lighting settings.

[0097] By distributing computing tasks to multiple computing nodes, this application allows the system to process massive amounts of data more quickly, improving overall processing efficiency and response speed, and ensuring that the system can still maintain efficient operation in large-scale applications.

[0098] In some optional implementations of this embodiment, after the steps of generating a target intelligent lighting solution based on the user demand information and controlling the intelligent lighting system to execute the intelligent lighting solution, the following steps are further included:

[0099] The historical user data, the user behavior similarity and the user demand information are stored in a preset blockchain node.

[0100] In this embodiment, the storage of historical user data, user behavior similarity, and user demand information is crucial during task processing in a smart lighting system, particularly to ensure data reliability, traceability, and security. Storing this data in blockchain nodes ensures that the data is tamper-proof throughout its lifecycle and can be backtracked and verified at different points in time. Blockchain is a distributed ledger technology that maintains data consistency and integrity across multiple nodes. Each block contains a set of data and is linked to the previous block, forming an immutable data structure. Using blockchain technology ensures a high degree of transparency, verifiability, and security for stored data. In smart lighting systems, historical user data, behavior similarity, and demand information are often sensitive data and may involve user privacy. Storing this data in a blockchain ensures that the data is tamper-proof and provides a foundation of trust for various nodes in the system (e.g., different computing nodes, sensors, etc.). Suppose a smart lighting system needs to store historical user light on / off data, device status, and user demand forecast information. If this data is stored in a traditional database, there is a risk of tampering or loss. By using blockchain technology, all data is recorded in the blockchain with a timestamp. Each data block cannot be modified or deleted, ensuring data security and credibility. For example, user A's behavioral data includes light on and off times, lighting requirements, etc. The system stores this data on the blockchain along with similarity calculation results and predicted demand information. This data can be securely accessed and verified by different system nodes (such as user terminals and control centers), ensuring data consistency.

[0101] This application enhances data security and transparency by storing user data, similarity, and demand information in blockchain nodes after generating a smart lighting solution and controlling the system execution. Blockchain technology provides an unalterable storage mechanism, ensuring data integrity and security, preventing data from being tampered with or lost, and improving system reliability and user trust.

[0102] It should be emphasized that in order to further ensure the privacy and security of the above-mentioned historical user data, the above-mentioned user behavior similarity and the above-mentioned user demand information, the above-mentioned historical user data, the above-mentioned user behavior similarity and the above-mentioned user demand information can also be stored in a node of a blockchain.

[0103] The blockchain referred to in this application is a new application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks generated using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of this information (to prevent counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer.

[0104] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0105] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0106] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware via computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes in the above-described method embodiments. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0107] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0108] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a task processing capability optimization device for an intelligent lighting system. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0109] like Figure 3 As shown, the task processing capability optimization device 300 for an intelligent lighting system according to this embodiment includes: an acquisition module 301, a calculation module 302, a prediction module 303, and a generation module 304.

[0110] An acquisition module 301 is configured to acquire historical user data of the intelligent lighting system to be optimized;

[0111] A calculation module 302 is configured to calculate the historical user data according to a preset similarity calculation model to obtain user behavior similarity;

[0112] Prediction module 303, used to predict the user behavior similarity based on a preset behavior prediction model to obtain user demand information;

[0113] The generating module 304 is configured to generate a target intelligent lighting solution according to the user demand information and control the intelligent lighting system to execute the intelligent lighting solution.

[0114] The task processing capability optimization device for an intelligent lighting system provided in this application obtains historical user data and processes the data using a similarity calculation model, thereby predicting user needs and generating a target intelligent lighting solution. This enables the intelligent lighting system to dynamically adjust the lighting strategy based on the user's actual behavior, thereby improving the intelligence and personalization level of the system, avoiding the limitations of traditional rule-based control methods, and enhancing the user experience and the system's operating efficiency and task processing capabilities.

[0115] In some optional implementations of this embodiment, the calculation module 302 is further configured to:

[0116] Obtain user behavior data related to smart lighting;

[0117] Preprocessing the user behavior data to obtain a feature data set;

[0118] Constructing the similarity calculation model according to the feature data set and a preset first deep learning algorithm;

[0119] The behavior prediction model is constructed based on the feature data set and a preset second deep learning algorithm.

[0120] The task processing capability optimization device for intelligent lighting systems provided in this application preprocesses data and extracts effective feature data sets, providing high-quality input data for subsequent similarity calculations and behavior predictions, thereby further improving the prediction accuracy of the model.

[0121] In some optional implementations of this embodiment, the calculation module 302 is further configured to:

[0122] Performing data segmentation on the feature data set to obtain a first training set and a first test set;

[0123] Establishing a first initial model by the convolutional neural network algorithm;

[0124] Performing model training on the first initial model according to the first training set to obtain a trained first target model;

[0125] The first target model is optimized according to the first test set to obtain the similarity calculation model.

[0126] The task processing capability optimization device for an intelligent lighting system provided in this application can more accurately mine the potential patterns and regularities in user behavior by using deep learning algorithms such as convolutional neural networks (CNN) for similarity calculation; through data segmentation and training optimization, an efficient similarity calculation model can be obtained, enabling the system to better identify and predict user behavior, provide personalized lighting control, and improve the accuracy and response speed of the intelligent lighting system.

[0127] In some optional implementations of this embodiment, the calculation module 302 is further configured to:

[0128] Performing data segmentation on the feature data set to obtain a second training set and a second test set;

[0129] Establishing a second initial model by the adaptive learning algorithm;

[0130] Performing model training on the second initial model according to the second training set to obtain a trained second target model;

[0131] The second target model is optimized according to the second test set to obtain the behavior prediction model.

[0132] The task processing capability optimization device for an intelligent lighting system provided in this application, through continuous learning and adjustment, can still provide accurate prediction results with limited training data, reduce computational complexity, improve the real-time application capability of the algorithm, and adapt to rapidly changing user needs.

[0133] In some optional implementations of this embodiment, the calculation module 302 is further configured to:

[0134] Performing data cleaning, data integration, data transformation, and data reduction on the user behavior data to obtain data to be extracted;

[0135] Feature extraction is performed on the data to be extracted to obtain the feature data set.

[0136] The task processing capability optimization device for an intelligent lighting system provided in this application can extract valuable information for prediction through feature extraction, build a more accurate feature data set, provide efficient data support for similarity calculation and behavior prediction, and improve the accuracy of prediction and the intelligence level of the system.

[0137] In some optional implementations of this embodiment, in the computing module 302, the similarity calculation model and the behavior prediction model adopt a distributed computing framework, the similarity calculation model processes the historical user data in parallel through multiple computing nodes, and the behavior prediction model processes the user behavior similarity in parallel through multiple computing nodes.

[0138] The task processing capability optimization device for an intelligent lighting system provided in this application distributes computing tasks to multiple computing nodes, allowing the system to process massive amounts of data more quickly, thereby improving overall processing efficiency and response speed, and ensuring that the system can still maintain efficient operation in large-scale applications.

[0139] In some optional implementations of this embodiment, the generating module 304 is further configured to:

[0140] The historical user data, the user behavior similarity and the user demand information are stored in a preset blockchain node.

[0141] The task processing capacity optimization device for an intelligent lighting system provided in this application enhances the security and transparency of data by storing user data, similarity, and demand information in blockchain nodes after generating an intelligent lighting plan and controlling the execution of the system. Blockchain technology provides an unalterable storage mechanism, ensures the integrity and security of the data, prevents data from being tampered with or lost, and improves the reliability of the system and the user's sense of trust.

[0142] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0143] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0144] The computer device may be a desktop computer, notebook computer, PDA, cloud server, etc. The computer device may interact with the user via a keyboard, mouse, remote control, touchpad, or voice control device.

[0145] The memory 41 includes at least one type of readable storage medium, including flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, a magnetic disk, an optical disk, etc. In some embodiments, the memory 41 may be an internal storage unit of the computer device 4, such as the hard disk or internal memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 4. Of course, the memory 41 may also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions for the task processing capacity optimization method of the intelligent lighting system. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0146] In some embodiments, the processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to execute computer-readable instructions or process data stored in the memory 41, such as executing computer-readable instructions for the method for optimizing task processing capacity of an intelligent lighting system.

[0147] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0148] The computer device provided in this application obtains historical user data and processes the data using a similarity calculation model, thereby predicting user needs and generating target intelligent lighting solutions. It enables the intelligent lighting system to dynamically adjust lighting strategies based on the user's actual behavior, thereby improving the intelligence and personalization level of the system, avoiding the limitations of traditional rule-based control methods, and enhancing user experience and the system's operating efficiency and task processing capabilities.

[0149] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the task processing capacity optimization method for an intelligent lighting system as described above.

[0150] The computer-readable storage medium provided in this application obtains historical user data and processes the data using a similarity calculation model, thereby predicting user needs and generating a target intelligent lighting solution. This enables the intelligent lighting system to dynamically adjust the lighting strategy based on the user's actual behavior, thereby improving the intelligence and personalization level of the system, avoiding the limitations of traditional rule-based control methods, and enhancing the user experience and the system's operating efficiency and task processing capabilities.

[0151] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0152] Obviously, the embodiments described above are only some of the embodiments of the present application, rather than all of the embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions described in the aforementioned specific embodiments, or to make equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the present application specification and the accompanying drawings, directly or indirectly used in other related technical fields, is also within the scope of patent protection of the present application.

Claims

1. A method for optimizing task processing capability of an intelligent lighting system, characterized in that: The steps include: Obtain historical user data of the smart lighting system to be optimized; Calculating the historical user data according to a preset similarity calculation model to obtain user behavior similarity; Predicting the user behavior similarity according to a preset behavior prediction model to obtain user demand information; According to the user demand information, a target intelligent lighting solution is generated and the intelligent lighting system is controlled to execute the intelligent lighting solution.

2. The task processing capability optimization method for an intelligent lighting system according to claim 1, characterized in that: Before the step of calculating the historical user data according to the preset similarity calculation model to obtain the user behavior similarity, the method further includes: Obtain user behavior data related to smart lighting; Preprocessing the user behavior data to obtain a feature data set; Constructing the similarity calculation model according to the feature data set and a preset first deep learning algorithm; The behavior prediction model is constructed according to the feature data set and a preset second deep learning algorithm.

3. The task processing capability optimization method for an intelligent lighting system according to claim 2, characterized in that: The first deep learning algorithm includes a convolutional neural network algorithm, and the step of constructing the similarity calculation model according to the feature data set and the preset first deep learning algorithm specifically includes: Performing data segmentation on the feature data set to obtain a first training set and a first test set; Establishing a first initial model by using the convolutional neural network algorithm; Performing model training on the first initial model according to the first training set to obtain a trained first target model; The first target model is optimized according to the first test set to obtain the similarity calculation model.

4. The task processing capability optimization method for an intelligent lighting system according to claim 2, characterized in that: The second deep learning algorithm includes an adaptive learning algorithm, and the step of constructing the behavior prediction model according to the feature data set and the preset second deep learning algorithm specifically includes: Performing data segmentation on the feature data set to obtain a second training set and a second test set; Establishing a second initial model by the adaptive learning algorithm; Performing model training on the second initial model according to the second training set to obtain a trained second target model; The second target model is optimized according to the second test set to obtain the behavior prediction model.

5. The task processing capability optimization method for an intelligent lighting system according to claim 2, characterized in that: The step of preprocessing the user behavior data to obtain a feature data set specifically includes: Performing data cleaning, data integration, data transformation and data reduction on the user behavior data to obtain data to be extracted; Perform feature extraction on the data to be extracted to obtain the feature data set.

6. The task processing capability optimization method for an intelligent lighting system according to claim 1, characterized in that: The similarity calculation model and the behavior prediction model adopt a distributed computing framework. The similarity calculation model processes the historical user data in parallel through multiple computing nodes, and the behavior prediction model processes the user behavior similarity in parallel through multiple computing nodes.

7. The task processing capability optimization method for an intelligent lighting system according to claim 1, characterized in that: After the step of generating a target intelligent lighting solution according to the user demand information and controlling the intelligent lighting system to execute the intelligent lighting solution, the method further includes: The historical user data, the user behavior similarity and the user demand information are stored in a preset blockchain node.

8. A task processing capability optimization device for an intelligent lighting system, characterized in that: include: An acquisition module, used for acquiring historical user data of the intelligent lighting system to be optimized; A calculation module, used to calculate the historical user data according to a preset similarity calculation model to obtain user behavior similarity; A prediction module, used to predict the user behavior similarity according to a preset behavior prediction model to obtain user demand information; A generation module is used to generate a target intelligent lighting solution according to the user demand information and control the intelligent lighting system to execute the intelligent lighting solution.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the method for optimizing task processing capability for an intelligent lighting system as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the task processing capability optimization method for an intelligent lighting system according to any one of claims 1 to 7 are implemented.

Images