Airport illumination control method and device based on artificial intelligence, equipment and medium

By using an AI-based airport lighting control method, which automatically adjusts brightness using sensor data and predictive models, the high energy consumption and slow response of traditional airport lighting systems are solved, achieving efficient energy saving and intelligent management of airport lighting.

CN118984513APending Publication Date: 2024-11-19SHENZHEN ZHONGFUNENG ELECTRIC EQUIPMENT CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411138693.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-19
Publication Date
2024-11-19

AI Technical Summary

Technical Problem

Traditional airport lighting systems rely on manual intervention or simple automated control, resulting in high energy consumption, slow response, and high maintenance costs, making it difficult to meet the high efficiency, energy saving, and intelligent requirements of modern airports.

Method used

An AI-based airport lighting control method is adopted. By acquiring sensor data, a pre-trained lighting demand prediction model is used to predict brightness, generate brightness adjustment commands, and automatically adjust the brightness of lighting equipment through a control interface.

Benefits of technology

It enables rapid and accurate control of airport lighting, reduces unnecessary energy consumption, lowers operating costs, and achieves intelligent management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118984513A_ABST
    Figure CN118984513A_ABST
Patent Text Reader

Abstract

The invention provides an airport lighting control method and device based on artificial intelligence, computer equipment and a storage medium. The method comprises the following steps: acquiring illumination brightness demand data in a target area of an airport acquired based on a preset sensor; preprocessing the illumination brightness demand data to obtain target illumination brightness demand data; calling a pre-trained illumination demand prediction model to perform prediction processing on the target illumination brightness demand data to obtain an illumination brightness prediction result; converting the illumination brightness prediction result into a target brightness level based on a mapping rule; generating a brightness adjustment instruction based on the target brightness level; and sending the brightness adjustment instruction to a lighting equipment actuator in the target area based on the control interface so as to control the lighting equipment actuator to carry out brightness adjustment processing on a lighting lamp in the target area according to the brightness adjustment instruction. According to the invention, rapid and accurate control of the lighting lamp of the airport is realized, and lighting energy consumption and operation cost of the airport are effectively reduced.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of communication technology, and in particular to an airport lighting control method, device, computer equipment and storage medium based on artificial intelligence. Background Art

[0002] With the increasing traffic volume and technological advancement, airport lighting management has become increasingly complex and important. In the complex and ever-changing airport environment, traditional lighting control systems can no longer meet the needs of modern airports for high efficiency, energy saving, safety and intelligence.

[0003] In the prior art, the lighting systems used in airports mostly rely on manual intervention or simple automatic control, and have problems such as high energy consumption, slow response, and high maintenance costs. Summary of the invention

[0004] The main purpose of the present invention is to provide an airport lighting control method, device, computer equipment and storage medium based on artificial intelligence, aiming to solve the technical problems in the prior art that the lighting systems used in airports mostly rely on manual intervention or simple automatic control, and have high energy consumption, slow response and high maintenance costs.

[0005] To achieve the above object, the present invention provides an airport lighting control method based on artificial intelligence, the method comprising:

[0006] Acquire lighting brightness demand data in a target area of ​​an airport collected based on preset sensors; wherein the lighting brightness demand data at least includes ambient light intensity data, temperature data, humidity data, and passenger flow data;

[0007] Preprocessing the lighting brightness requirement data to obtain corresponding target lighting brightness requirement data;

[0008] Call the pre-trained lighting demand prediction model;

[0009] Based on the lighting demand prediction model, the target lighting brightness demand data is predicted and processed to obtain a corresponding lighting brightness prediction result;

[0010] Converting the lighting brightness prediction result into a corresponding target brightness level based on a preset mapping rule;

[0011] generating a corresponding brightness adjustment instruction based on the target brightness level;

[0012] The brightness adjustment instruction is sent to the lighting device actuator in the target area based on a preset control interface, so as to control the lighting device actuator to perform corresponding brightness adjustment processing on the lighting fixtures in the target area according to the brightness adjustment instruction.

[0013] Optionally, before calling the pre-trained lighting demand prediction model, the method further includes:

[0014] Collect initial data related to lighting intensity requirements from pre-defined data sources;

[0015] Performing sample construction processing on the initial data to obtain corresponding lighting sample data;

[0016] Dividing the lighting sample data into a training set and a test set;

[0017] Call the preset decision tree model;

[0018] Training the decision tree model based on the training set to obtain a corresponding designated decision tree model;

[0019] Performing a performance test on the specified decision tree model based on the test set;

[0020] If the designated decision tree model passes the performance test, the designated decision tree model is used as the lighting demand prediction model.

[0021] Optionally, after performing a performance test on the designated decision tree model based on the test set, the method further includes:

[0022] If the specified decision tree model fails the performance test, a preset model tuning strategy is obtained;

[0023] Tuning the specified decision tree model based on the model tuning strategy to obtain a corresponding target decision tree model;

[0024] Get the preset model storage method;

[0025] The target decision tree model is stored based on the model storage method.

[0026] Optionally, preprocessing the lighting brightness requirement data to obtain corresponding target lighting brightness requirement data includes:

[0027] Performing data cleaning processing on the lighting brightness demand data to obtain corresponding first processed data;

[0028] Performing feature engineering processing on the first processed data to obtain corresponding second processed data;

[0029] Performing format conversion processing on the second processed data to obtain corresponding third processed data;

[0030] The third processed data is used as the target lighting brightness requirement data.

[0031] Optionally, preprocessing the lighting brightness requirement data to obtain corresponding target lighting brightness requirement data includes:

[0032] Get the preset mapping function;

[0033] Performing data mapping processing on the lighting brightness prediction result based on the mapping function to obtain mapping data corresponding to the lighting brightness prediction result;

[0034] The mapping data is used as the target brightness level.

[0035] Optionally, after acquiring the lighting brightness requirement data in the target area of ​​the airport collected by the preset sensor, the method further includes:

[0036] Acquire the position movement information of the target passenger in the target area; wherein the movement information includes position information and movement direction information;

[0037] Get the preset brightness adjustment strategy;

[0038] Determining a target lighting fixture corresponding to the position movement information;

[0039] Based on the brightness adjustment strategy, corresponding brightness adjustment processing is performed on the target lighting fixture.

[0040] Optionally, after the preset control interface sends the brightness adjustment instruction to the lighting device actuator in the target area to control the lighting device actuator to perform corresponding brightness adjustment processing on the lighting fixtures in the target area according to the brightness adjustment instruction, the method further includes:

[0041] Monitoring working state parameters of lighting fixtures within the target area based on target sensors;

[0042] Performing data analysis on the working status parameters to determine whether the lighting fixture has a fault;

[0043] If so, generating warning information corresponding to the fault;

[0044] Obtaining a solution corresponding to the fault;

[0045] The warning information and the solution are sent to a preset maintenance personnel.

[0046] In addition, to achieve the above-mentioned purpose, the present invention also provides an airport lighting control device based on artificial intelligence, and the airport lighting control device based on artificial intelligence includes:

[0047] A first acquisition module is used to acquire lighting brightness demand data in a target area of ​​an airport collected based on a preset sensor; wherein the lighting brightness demand data at least includes ambient light intensity data, temperature data, humidity data, and passenger flow data;

[0048] A preprocessing module, used to preprocess the lighting brightness requirement data to obtain corresponding target lighting brightness requirement data;

[0049] The first calling module is used to call the pre-trained lighting demand prediction model;

[0050] A prediction module, used to perform prediction processing on the target lighting brightness demand data based on the lighting demand prediction model to obtain a corresponding lighting brightness prediction result;

[0051] A mapping module, used to convert the lighting brightness prediction result into a corresponding target brightness level based on a preset mapping rule;

[0052] A first generating module, configured to generate a corresponding brightness adjustment instruction based on the target brightness level;

[0053] The first sending module is used to send the brightness adjustment instruction to the lighting device actuator in the target area based on a preset control interface, so as to control the lighting device actuator to perform corresponding brightness adjustment processing on the lighting fixtures in the target area according to the brightness adjustment instruction. In order to solve the above technical problems, the embodiment of the present application also provides a computer device, which adopts the following technical solution:

[0054] The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the artificial intelligence-based airport lighting control methods proposed in the embodiments of the present application are implemented.

[0055] 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:

[0056] The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of any one of the artificial intelligence-based airport lighting control methods proposed in the embodiments of the present application are implemented.

[0057] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0058] The present invention provides an airport lighting control method, device, computer equipment and storage medium based on artificial intelligence. The method comprises: firstly obtaining lighting brightness demand data in a target area of ​​an airport collected based on a preset sensor; wherein the lighting brightness demand data at least includes ambient light intensity data, temperature data, humidity data and pedestrian flow data; then preprocessing the lighting brightness demand data to obtain corresponding target lighting brightness demand data; then calling a pre-trained lighting demand prediction model, and predicting and processing the target lighting brightness demand data based on the lighting demand prediction model to obtain a corresponding lighting brightness prediction result; subsequently converting the lighting brightness prediction result into a corresponding target brightness level based on a preset mapping rule; further generating a corresponding brightness adjustment instruction based on the target brightness level; finally sending the brightness adjustment instruction to a lighting device actuator in the target area based on a preset control interface to control the lighting device actuator to perform corresponding brightness adjustment processing on the lighting fixtures in the target area according to the brightness adjustment instruction. The present application utilizes artificial intelligence technology and a lighting demand prediction model to quickly and accurately generate lighting brightness prediction results corresponding to the collected airport lighting brightness demand data, and then converts the lighting brightness prediction results into corresponding target brightness levels based on mapping rules, and automatically sends brightness adjustment instructions corresponding to the target brightness level to the lighting equipment actuator in the target area based on the use of a control interface, so as to control the lighting equipment actuator to perform corresponding brightness adjustment processing on the lighting fixtures in the target area according to the brightness adjustment instructions, thereby achieving rapid and accurate control of the airport's lighting fixtures, thereby reducing unnecessary lighting energy consumption, reducing airport operating costs, and effectively realizing intelligent control of airport lighting. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0060] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0061] Figure 2 is a flow chart of an airport lighting control method based on artificial intelligence provided by an embodiment of the present invention;

[0062] Figure 3 is a structural schematic diagram of an embodiment of an artificial intelligence-based airport lighting control device according to the present application;

[0063] Figure 4 This is a basic structural block diagram of the computer device in this embodiment. DETAILED DESCRIPTION

[0064] The artificial intelligence-based airport lighting control method provided by the embodiment of the present invention is applied to the artificial intelligence-based airport lighting control device. Unless otherwise defined, all technical and scientific terms used in this document have the same meaning as those generally understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned drawings and any variations thereof 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.

[0065] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0066] 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.

[0067] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0068] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social online platform software, etc.

[0069] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0070] 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 .

[0071] It should be noted that the artificial intelligence-based airport lighting control method provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the artificial intelligence-based airport lighting control device is generally arranged in the server / terminal device.

[0072] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0073] With the increasing traffic volume and technological advancement, airport lighting management has become increasingly complex and important. In the complex and ever-changing airport environment, traditional lighting control systems can no longer meet the needs of modern airports for high efficiency, energy saving, safety and intelligence.

[0074] In the prior art, the lighting systems used in airports mostly rely on manual intervention or simple automatic control, and have problems such as high energy consumption, slow response, and high maintenance costs.

[0075] Continue to refer Figure 2 , shows a flow chart of an embodiment of an airport lighting control method based on artificial intelligence proposed in the present application. The embodiment of the present application can acquire and process relevant data based on artificial intelligence technology.

[0076] The airport lighting control method based on artificial intelligence provided by the embodiment of the present invention comprises the following steps:

[0077] S210, obtaining lighting brightness requirement data in a target area of ​​an airport collected based on preset sensors; wherein the lighting brightness requirement data at least includes ambient light intensity data, temperature data, humidity data, and passenger flow data.

[0078] In this step, the present invention can be applied to the business scenario of intelligent lighting control of lighting fixtures in airports, and the execution subject of the present invention can be specifically an airport lighting control system. Among them, high-performance sensors and lighting equipment actuators are pre-selected and deployed according to the preset layout plan. Ensure that the sensors can fully cover all areas of the airport and accurately collect environmental parameters and lighting demand brightness data; the lighting equipment actuator can accurately execute control commands to achieve precise control of the lighting brightness and color temperature of the lighting fixtures. The above-mentioned target area may include any one or more areas of the airport's boarding gate, terminal, baggage claim area, etc. Among them, the above-mentioned preset sensors may include at least light sensors, temperature sensors, humidity sensors, and crowd flow sensors. Specifically, light sensors: installed in various key areas inside the airport (such as terminal halls, boarding gates, baggage claim areas, etc.), used to monitor the ambient light intensity in real time, so as to adjust artificial lighting according to the natural light intensity. Temperature sensors and humidity sensors: also deployed in various key areas inside the airport, used to collect indoor temperature and humidity data, and assist in adjusting the lighting system to create a more comfortable environment. Crowd flow sensors (such as infrared sensors or video analysis equipment): deployed in crowded areas such as entrances, exits, boarding gates, etc., to monitor crowd density in real time to adjust lighting brightness and direction, optimize energy use and enhance passenger experience. In addition, other sensors (such as air pressure sensors, wind speed sensors, etc.) may also be included: in specific cases (such as outdoor apron lighting), they can be deployed as needed to cope with extreme weather conditions. In addition, all sensors are connected to the airport's data acquisition network via wired or wireless means, such as low-power wide area networks such as Wi-Fi, Zigbee or LoRa. The data acquisition system collects sensor data regularly or in real time, and after preliminary processing (such as denoising, data compression), it is transmitted to the airport lighting control system.

[0079] S220, preprocessing the lighting brightness requirement data to obtain corresponding target lighting brightness requirement data.

[0080] In this step, the specific implementation process of preprocessing the lighting brightness requirement data to obtain the corresponding target lighting brightness requirement data will be further described in detail in subsequent specific embodiments of the present application, and will not be elaborated on here.

[0081] S230, calling a pre-trained lighting demand prediction model.

[0082] In this step, a trained lighting demand prediction model can be loaded by using a machine learning library (such as scikit-learn). The lighting demand prediction model is generated by training a decision tree model based on pre-built lighting sample data. The specific model construction process will be further described in detail in the subsequent specific embodiments of this application, and will not be elaborated on here.

[0083] S240: performing prediction processing on the target lighting brightness demand data based on the lighting demand prediction model to obtain a corresponding lighting brightness prediction result.

[0084] In this step, the target lighting brightness demand data can be input into the above-mentioned lighting demand prediction model to implement prediction processing of the target lighting brightness demand data through the predict() method of the lighting demand prediction model, and output the corresponding lighting brightness prediction result.

[0085] S250: Convert the lighting brightness prediction result into a corresponding target brightness level based on a preset mapping rule.

[0086] In this step, the specific implementation process of converting the lighting brightness prediction result into the corresponding target brightness level based on the preset mapping rule will be further described in detail in the subsequent specific embodiments of the present application, and will not be elaborated here.

[0087] S260: Generate a corresponding brightness adjustment instruction based on the target brightness level.

[0088] In this step, the target brightness level can be input into the to-be-filled area corresponding to the brightness level in the preset brightness adjustment instruction template to obtain the brightness adjustment instruction. The brightness adjustment instruction template is a pre-built instruction template for interacting with the lighting device actuator for control instructions, and the content of the instruction template can be set according to actual needs.

[0089] S270: Send the brightness adjustment instruction to the lighting device actuator in the target area based on a preset control interface to control the lighting device actuator to perform corresponding brightness adjustment processing on the lighting fixtures in the target area according to the brightness adjustment instruction.

[0090] In this step, the control interface is a pre-built interface for communicating with a lighting device actuator. The lighting device actuator may include a dimming driver, a switch controller, etc. The lighting device actuator is used to achieve precise control of the lighting brightness and color temperature of the lighting fixture.

[0091] In an embodiment of the present invention, firstly, the lighting brightness demand data in the target area of ​​the airport collected based on the preset sensor is obtained; wherein the lighting brightness demand data at least includes ambient light intensity data, temperature data, humidity data and pedestrian flow data; then, the lighting brightness demand data is preprocessed to obtain corresponding target lighting brightness demand data; then, a pre-trained lighting demand prediction model is called, and the target lighting brightness demand data is predicted and processed based on the lighting demand prediction model to obtain a corresponding lighting brightness prediction result; subsequently, the lighting brightness prediction result is converted into a corresponding target brightness level based on a preset mapping rule; further, a corresponding brightness adjustment instruction is generated based on the target brightness level; finally, the brightness adjustment instruction is sent to the lighting device actuator in the target area based on a preset control interface to control the lighting device actuator to perform corresponding brightness adjustment processing on the lighting fixtures in the target area according to the brightness adjustment instruction. The present application utilizes artificial intelligence technology and a lighting demand prediction model to quickly and accurately generate lighting brightness prediction results corresponding to the collected airport lighting brightness demand data, and then converts the lighting brightness prediction results into corresponding target brightness levels based on mapping rules, and automatically sends brightness adjustment instructions corresponding to the target brightness level to the lighting equipment actuator in the target area based on the use of a control interface, so as to control the lighting equipment actuator to perform corresponding brightness adjustment processing on the lighting fixtures in the target area according to the brightness adjustment instructions, thereby achieving rapid and accurate control of the airport's lighting fixtures, thereby reducing unnecessary lighting energy consumption, reducing airport operating costs, and effectively realizing intelligent control of airport lighting.

[0092] Optionally, before calling the pre-trained lighting demand prediction model, the method further includes:

[0093] Gather initial data related to lighting level requirements from pre-defined data sources.

[0094] In this step, the data source may include sensors, historical records, databases, etc. The initial data may include multiple features, such as time (date, timestamp), location information (room number, floor, etc.), environmental parameters (external light intensity, temperature, humidity, etc.), and human traffic.

[0095] The initial data is subjected to sample construction processing to obtain corresponding lighting sample data.

[0096] In this step, the initial data can be cleaned, feature engineered, and processed as target variables to complete the sample construction process and obtain the corresponding lighting sample data. Data cleaning includes: checking and processing missing values, outliers, duplicate records, etc. in the data. For example, the mean, median, or mode can be used to fill missing values, and outliers can be deleted or corrected. Feature engineering includes: extracting and constructing useful features based on business needs and data characteristics. For example, the hourly and daily change rates of pedestrian traffic can be calculated, and the timestamp can be converted into categorical features such as hours, days of the week, and months. Target variable processing: Determine the target variable (i.e., lighting brightness requirements) and convert it into a format that the model can process. If the target variable is continuous (such as a specific brightness value), it needs to be discretized into categories (such as "low", "medium", and "high"), or retained as a continuous value and a regression tree is used.

[0097] The lighting sample data is divided into a training set and a test set.

[0098] In this step, the lighting sample data can be divided into corresponding training sets and test sets according to a preset division ratio. There is no specific limitation on the numerical selection of the division ratio, which can be set according to actual model training requirements, for example, 8:2.

[0099] Call the preset decision tree model.

[0100] In this step, by selecting decision tree as the model type. In Python, for classification problems, you can use DecisionTreeClassifier from the scikit-learn library, or, for regression problems, you can use DecisionTreeRegressor as a decision tree model.

[0101] The decision tree model is trained based on the training set to obtain a corresponding designated decision tree model.

[0102] In this step, the decision tree model is trained by using the training set. During the training process, the decision tree model learns how to map the input features to the target variables, thereby obtaining a trained designated decision tree model. The specific training process of the designated decision tree model can refer to the training process of the general decision tree model, and will not be described in detail here.

[0103] A performance test is performed on the designated decision tree model based on the test set.

[0104] In this step, the performance of the decision tree specified by the model obtained by using the test set evaluation is calculated, that is, the accuracy, precision and recall indicators of the specified decision tree model on the test set are calculated, and at the same time, it is determined whether the accuracy is greater than the preset accuracy threshold, whether the precision is greater than the preset precision threshold, and whether the recall is greater than the preset recall threshold. If the accuracy, precision and recall of the specified decision tree model on the test set are all greater than the corresponding preset thresholds, then the specified decision tree model is determined to have passed the performance test, otherwise it is determined that the specified decision tree model has not passed the performance test. Among them, there is no specific limitation on the values ​​of the above-mentioned accuracy threshold, precision threshold and recall threshold, and they can be set according to the actual model evaluation requirements.

[0105] If the designated decision tree model passes the performance test, the designated decision tree model is used as the lighting demand prediction model.

[0106] In this step, if it is detected that the designated decision tree model passes the performance test, it indicates that the performance of the designated decision tree model meets the requirements, and then the designated decision tree model is used as the lighting demand prediction model.

[0107] In this embodiment, initial data related to lighting brightness requirements are collected from a preset data source; then the initial data is processed by sample construction to obtain corresponding lighting sample data, and the lighting sample data is divided into a training set and a test set; then a preset decision tree model is called; and the decision tree model is trained based on the training set to obtain a corresponding designated decision tree model; subsequently, a performance test is performed on the designated decision tree model based on the test set; if the designated decision tree model passes the performance test, the designated decision tree model is used as the lighting demand prediction model. This application collects initial data related to lighting brightness requirements from a preset data source, and processes the initial data by sample construction to obtain corresponding lighting sample data, and then uses the lighting sample data to train and test the preset decision tree model, so as to realize the rapid and accurate construction of the required lighting demand prediction model, improve the construction efficiency of the lighting demand prediction model, and ensure the model effect of the obtained lighting demand prediction model.

[0108] Optionally, after performing a performance test on the designated decision tree model based on the test set, the method further includes:

[0109] If the specified decision tree model fails the performance test, a preset model tuning strategy is obtained.

[0110] In this step, if it is detected that the specified decision tree model fails the performance test, it indicates that the performance of the specified decision tree model does not meet the requirements. The above-mentioned model tuning strategy may specifically include adjusting the parameters of the model, such as the depth of the tree, the minimum number of samples required for splitting, the minimum number of samples in the leaf nodes, etc., or using cross-validation to find a better combination of parameters, or using ensemble learning methods (such as random forests, gradient boosting trees) to further improve the performance of the model.

[0111] The designated decision tree model is tuned based on the model tuning strategy to obtain a corresponding target decision tree model.

[0112] In this step, the designated decision tree model may be subjected to matching tuning processing according to the tuning operation content in the above-mentioned model tuning strategy to obtain a tuned target decision tree model.

[0113] Get the preset model storage method.

[0114] In this step, there is no specific limitation on the selection of the above-mentioned model storage method, which can be set according to the actual model storage requirements, for example, it may include blockchain storage, local database storage, cloud server storage, etc.

[0115] The target decision tree model is stored based on the model storage method.

[0116] In this step, by determining a storage medium corresponding to the above-mentioned model storage method, the target decision tree model is stored in the above-mentioned storage medium to complete the standardized and intelligent storage processing of the target decision tree model.

[0117] In this embodiment, if the specified decision tree model fails the performance test, a preset model tuning strategy is obtained; then the specified decision tree model is tuned based on the model tuning strategy to obtain a corresponding target decision tree model; then a preset model storage method is obtained; and the target decision tree model is subsequently stored based on the model storage method. When the present application detects that the specified decision tree model fails the performance test, the model tuning strategy will be intelligently used to tune the specified decision tree model to improve the performance of the model, thereby obtaining a target decision tree model that meets the performance requirements. The target decision tree model will also be stored using the model storage method later so that it can be used directly without retraining, thereby improving the intelligence of the model storage.

[0118] Optionally, preprocessing the lighting brightness requirement data to obtain corresponding target lighting brightness requirement data includes:

[0119] The lighting brightness requirement data is cleaned to obtain corresponding first processed data.

[0120] In this step, the data cleaning process specifically includes checking and processing missing values, outliers, duplicate records, etc. in the data. For example, the mean, median or mode is used to fill missing values, and outliers are deleted or corrected.

[0121] Perform feature engineering processing on the first processed data to obtain corresponding second processed data.

[0122] In this step, the feature engineering processing refers to extracting and constructing useful features according to business needs and data characteristics, that is, extracting the same features as those used to train the lighting demand prediction model from the first processed data, which may specifically include time features, spatial features, crowd flow features, and environmental features. Among them, time features: extracting features such as hours, days of the week, and months from timestamps to capture seasonal or periodic changes. Spatial features: according to the sensor location information, the airport is divided into different areas or grids, and the corresponding spatial location features are extracted. Crowd flow features: based on the data of the crowd flow sensor, calculate features such as crowd flow, crowd density, and crowd speed. Environmental features: including environmental parameters such as light intensity, temperature, and humidity.

[0123] The second processed data is format converted to obtain corresponding third processed data.

[0124] In this step, the format conversion process refers to a process of converting the format into a format that can be processed by the model.

[0125] The third processed data is used as the target lighting brightness requirement data.

[0126] In this embodiment, the lighting brightness demand data is cleaned to obtain corresponding first processed data; the first processed data is then subjected to feature engineering to obtain corresponding second processed data; the second processed data is then subjected to format conversion to obtain corresponding third processed data; the third processed data is subsequently used as the target lighting brightness demand data. This application performs data cleaning, feature engineering, and format conversion on the acquired lighting brightness demand data, thereby enabling fast and intelligent preprocessing of the lighting brightness demand data, effectively ensuring the accuracy of the obtained target lighting brightness demand data, and thus facilitating the improvement of the prediction accuracy of the subsequent prediction of the target lighting brightness demand data using the lighting demand prediction model.

[0127] Optionally, preprocessing the lighting brightness requirement data to obtain corresponding target lighting brightness requirement data includes:

[0128] Get the preset mapping function.

[0129] In this step, according to the actual application scenario and specific needs, the brightness levels corresponding to each category label of the output of the lighting demand prediction model are pre-defined to form the corresponding mapping logic. Specifically, the category labels include low, medium, and high, and the category labels "low", "medium", and "high" are respectively mapped to a sub-interval of the brightness value range. Exemplarily, the specific brightness levels corresponding to the category labels "low", "medium", and "high" are brightness levels of 10%, 50%, and 100%, respectively. A mapping function matching the above mapping logic is pre-written, which accepts a category label as input and returns the corresponding brightness level. Specifically, the above mapping function can be implemented using conditional statements (such as if-elif-else) or dictionary mapping.

[0130] The lighting brightness prediction result is subjected to data mapping processing based on the mapping function to obtain mapping data corresponding to the lighting brightness prediction result.

[0131] In this step, the above-mentioned lighting brightness prediction result can be input into the mapping function to perform data mapping processing on the lighting brightness prediction result through the mapping function, and output mapping data corresponding to the lighting brightness prediction result, which is a numerical value corresponding to a brightness level.

[0132] The mapping data is used as the target brightness level.

[0133] In this embodiment, a preset mapping function is obtained; then, data mapping processing is performed on the lighting brightness prediction result based on the mapping function to obtain mapping data corresponding to the lighting brightness prediction result; and the mapping data is subsequently used as the target brightness level. The present application performs data mapping processing on the lighting brightness prediction result based on the use of a mapping function, which can realize the rapid and accurate generation of target lighting brightness demand data corresponding to the lighting brightness prediction result, improve the generation efficiency of the target lighting brightness demand data, and ensure the accuracy of the obtained target lighting brightness demand data.

[0134] Optionally, after acquiring the lighting brightness requirement data in the target area of ​​the airport collected by the preset sensor, the method further includes:

[0135] Acquire the position movement information of the target passenger in the target area; wherein the movement information includes position information and movement direction information.

[0136] In this step, the target passenger can be any passenger in the target area. The moving trajectory of the target passenger in the target area can be tracked by using video analysis technology or Bluetooth or Wi-Fi positioning technology, and then the position movement information of the target passenger can be obtained according to the moving trajectory. The movement information includes position information and moving direction information. The position information refers to the current position of the target passenger, and the movement information refers to the moving direction of the target passenger. The destination area of ​​the target passenger can be determined according to the current position and moving direction of the target passenger.

[0137] Get the preset brightness adjustment strategy.

[0138] In this step, the brightness adjustment strategy includes: increasing the lighting brightness of the specific area when the passenger approaches the specific area, and restoring the lighting brightness of the specific area to the original lighting brightness state when the passenger moves away from the specific area.

[0139] Determine a target lighting fixture corresponding to the position movement information.

[0140] In this step, after the arrival destination area of ​​the target passenger is determined through the above-mentioned position movement information, the above-mentioned target lighting fixture refers to the lighting fixture installed in the arrival destination area corresponding to the target passenger.

[0141] Based on the brightness adjustment strategy, corresponding brightness adjustment processing is performed on the target lighting fixture.

[0142] In this step, the target lighting fixture may be subjected to a matching brightness adjustment process according to the strategy content of the brightness adjustment strategy. The brightness adjustment process may include a process of increasing the lighting brightness or restoring the original lighting brightness state.

[0143] In this embodiment, the position movement information of the target passenger in the target area is obtained; wherein the movement information includes position information and movement direction information; then a preset brightness adjustment strategy is obtained; then the target lighting fixture corresponding to the position movement information is determined; and then the target lighting fixture is subjected to corresponding brightness adjustment processing based on the brightness adjustment strategy. The present application obtains the position movement information of the target passenger in the target area, and then intelligently performs corresponding brightness adjustment processing on the target lighting fixture corresponding to the position movement information based on the brightness adjustment strategy, so as to dynamically adjust the lighting intensity and direction, provide personalized navigation services for the target passengers, and help improve the user experience of the target passengers.

[0144] Optionally, after the preset control interface sends the brightness adjustment instruction to the lighting device actuator in the target area to control the lighting device actuator to perform corresponding brightness adjustment processing on the lighting fixtures in the target area according to the brightness adjustment instruction, the method further includes:

[0145] The operating status parameters of the lighting fixtures within the target area are monitored based on the target sensor.

[0146] In this step, the target sensor is a pre-configured sensor for monitoring the working state of the lighting fixtures in the target area, and may include, for example, a current sensor, a voltage sensor, a temperature sensor, etc. Correspondingly, the working state parameters include key parameters such as current, voltage, and temperature.

[0147] Perform data analysis on the working status parameters to determine whether the lighting fixture has a fault.

[0148] In this step, the working state parameters monitored by the target sensor can be analyzed in real time by using a machine learning algorithm to identify abnormal modes (such as excessive current, unstable voltage, excessive temperature, etc.) and predict potential faults. If at least one abnormal mode is identified in the lighting fixture, it is determined that the lighting fixture is faulty. If no abnormal mode is identified in the lighting fixture, it is determined that the lighting fixture is not faulty.

[0149] If so, generate warning information corresponding to the fault.

[0150] In this step, the above-mentioned warning information can be obtained by obtaining the fault location, fault type, and urgency of the fault and inputting them into a preset warning information template. The above-mentioned warning information template can be an information template constructed according to actual warning processing requirements.

[0151] Get the solution corresponding to the fault.

[0152] In this step, the solution corresponding to the fault can be found by searching a preset solution library, wherein the solution library is a pre-built database storing various faults and solutions corresponding to the various faults.

[0153] The warning information and the solution are sent to a preset maintenance personnel.

[0154] In this step, the maintenance personnel are the staff responsible for the maintenance of the lighting fixtures. The warning information and the solution can be sent to the maintenance personnel through the communication information of the maintenance personnel and according to the communication information. The communication information can include a mobile phone number or an email address.

[0155] In this embodiment, the working state parameters of the lighting fixtures in the target area are monitored based on the target sensor; then the working state parameters are analyzed to determine whether the lighting fixture has a fault; if so, a warning message corresponding to the fault is generated; then a solution corresponding to the fault is obtained; and subsequently the warning message and the solution are sent to the preset maintenance personnel. This application automatically monitors the working state parameters of the lighting fixtures in the target area based on the target sensor and performs data analysis. If a fault is detected in the lighting fixture, a warning message corresponding to the fault is intelligently generated, and a solution corresponding to the fault is obtained, and then the warning message and the solution are sent to the corresponding maintenance personnel in a timely manner, thereby helping the maintenance personnel to quickly locate the problem and take corresponding measures, improving the work experience of the maintenance personnel, and ensuring the normal and stable operation of the lighting fixtures, and improving the safety of the airport.

[0156] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of an airport lighting control device 300 based on artificial intelligence, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0157] An embodiment of the present invention provides an airport lighting control device 300 based on artificial intelligence. The airport lighting control device 300 based on artificial intelligence includes:

[0158] A first acquisition module 310 is used to acquire lighting brightness demand data in a target area of ​​an airport based on data collected by a preset sensor; wherein the lighting brightness demand data at least includes ambient light intensity data, temperature data, humidity data, and passenger flow data;

[0159] A preprocessing module 320, configured to preprocess the lighting brightness requirement data to obtain corresponding target lighting brightness requirement data;

[0160] A first calling module 330 is used to call a pre-trained lighting demand prediction model;

[0161] A prediction module 340 is used to perform prediction processing on the target lighting brightness demand data based on the lighting demand prediction model to obtain a corresponding lighting brightness prediction result;

[0162] A mapping module 350, configured to convert the lighting brightness prediction result into a corresponding target brightness level based on a preset mapping rule;

[0163] A first generating module 360, configured to generate a corresponding brightness adjustment instruction based on the target brightness level;

[0164] The first sending module 370 is used to send the brightness adjustment instruction to the lighting device actuator in the target area based on a preset control interface, so as to control the lighting device actuator to perform corresponding brightness adjustment processing on the lighting fixtures in the target area according to the brightness adjustment instruction.

[0165] Optionally, the artificial intelligence-based airport lighting control device 300 further includes:

[0166] A collection module, used for collecting initial data related to lighting brightness requirements from a preset data source;

[0167] A construction module, used for performing sample construction processing on the initial data to obtain corresponding lighting sample data;

[0168] A division module, used for dividing the lighting sample data into a training set and a test set;

[0169] The second calling module is used to call a preset decision tree model;

[0170] A training module, used to train the decision tree model based on the training set to obtain a corresponding designated decision tree model;

[0171] A testing module, used for performing a performance test on the specified decision tree model based on the test set;

[0172] The first determination module is used to use the designated decision tree model as the lighting demand prediction model if the designated decision tree model passes the performance test.

[0173] Optionally, the artificial intelligence-based airport lighting control device 300 further includes:

[0174] A second acquisition module is used to acquire a preset model tuning strategy if the specified decision tree model fails the performance test;

[0175] A tuning module, used to perform tuning processing on the specified decision tree model based on the model tuning strategy to obtain a corresponding target decision tree model;

[0176] A third acquisition module is used to acquire a preset model storage method;

[0177] A storage module is used to store the target decision tree model based on the model storage method.

[0178] Optionally, the preprocessing module 320 includes:

[0179] A first processing submodule, used for performing data cleaning processing on the lighting brightness demand data to obtain corresponding first processed data;

[0180] A second processing submodule, used for performing feature engineering processing on the first processed data to obtain corresponding second processed data;

[0181] A third processing submodule, used for performing format conversion processing on the second processed data to obtain corresponding third processed data;

[0182] The first determining submodule is configured to use the third processed data as the target lighting brightness requirement data.

[0183] Optionally, the mapping module 350 includes:

[0184] Get submodule, used to get preset mapping function;

[0185] A mapping submodule, configured to perform data mapping processing on the lighting brightness prediction result based on the mapping function to obtain mapping data corresponding to the lighting brightness prediction result;

[0186] The second determining submodule is configured to use the mapping data as the target brightness level.

[0187] Optionally, the artificial intelligence-based airport lighting control device 300 further includes:

[0188] A fourth acquisition module is used to acquire the position movement information of the target passenger in the target area; wherein the movement information includes position information and movement direction information;

[0189] A fifth acquisition module, used to acquire a preset brightness adjustment strategy;

[0190] A second determining module, used to determine a target lighting fixture corresponding to the position movement information;

[0191] An adjustment module is used to perform corresponding brightness adjustment processing on the target lighting fixture based on the brightness adjustment strategy.

[0192] Optionally, the artificial intelligence-based airport lighting control device 300 further includes:

[0193] A monitoring module, used for monitoring working status parameters of lighting fixtures in the target area based on a target sensor;

[0194] An analysis module, used to perform data analysis on the working status parameters to determine whether the lighting fixture has a fault;

[0195] A second generating module, configured to generate warning information corresponding to the fault if yes;

[0196] A sixth acquisition module, used to acquire a solution corresponding to the fault;

[0197] The second sending module is used to send the warning information and the solution to a preset maintenance personnel.

[0198] 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.

[0199] 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 (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0200] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0201] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), 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 memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can 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 the program code of the airport lighting control method based on artificial intelligence, etc. 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.

[0202] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. 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 run the program code stored in the memory 41 or process data, such as running the program code of the artificial intelligence-based airport lighting control method.

[0203] 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.

[0204] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores the application crash processing program, and the application crash processing program can be executed by at least one processor to enable the at least one processor to perform the steps of the above-mentioned artificial intelligence-based airport lighting control method.

[0205] 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 a necessary general hardware online platform, and of course, by hardware, but in many cases the former is a better implementation method. Based on such an 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 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.

[0206] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0207] Obviously, the embodiments described above are only some embodiments of the present application, rather than all 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 is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. An airport lighting control method based on artificial intelligence, characterized in that: include: Acquire lighting brightness demand data in a target area of ​​an airport collected based on preset sensors; wherein the lighting brightness demand data at least includes ambient light intensity data, temperature data, humidity data, and passenger flow data; Preprocessing the lighting brightness requirement data to obtain corresponding target lighting brightness requirement data; Call the pre-trained lighting demand prediction model; Based on the lighting demand prediction model, the target lighting brightness demand data is predicted and processed to obtain a corresponding lighting brightness prediction result; Converting the lighting brightness prediction result into a corresponding target brightness level based on a preset mapping rule; generating a corresponding brightness adjustment instruction based on the target brightness level; The brightness adjustment instruction is sent to the lighting device actuator in the target area based on a preset control interface, so as to control the lighting device actuator to perform corresponding brightness adjustment processing on the lighting fixtures in the target area according to the brightness adjustment instruction.

2. The method according to claim 1, characterized in that Before calling the pre-trained lighting demand prediction model, the method further includes: Collect initial data related to lighting intensity requirements from pre-defined data sources; Performing sample construction processing on the initial data to obtain corresponding lighting sample data; Dividing the lighting sample data into a training set and a test set; Call the preset decision tree model; Training the decision tree model based on the training set to obtain a corresponding designated decision tree model; Performing a performance test on the designated decision tree model based on the test set; If the designated decision tree model passes the performance test, the designated decision tree model is used as the lighting demand prediction model.

3. The method according to claim 2, characterized in that After performing a performance test on the designated decision tree model based on the test set, the method further includes: If the specified decision tree model fails the performance test, a preset model tuning strategy is obtained; Tuning the specified decision tree model based on the model tuning strategy to obtain a corresponding target decision tree model; Get the preset model storage method; The target decision tree model is stored based on the model storage method.

4. The method according to claim 1, characterized in that: The preprocessing of the lighting brightness requirement data to obtain corresponding target lighting brightness requirement data includes: Performing data cleaning processing on the lighting brightness demand data to obtain corresponding first processed data; Performing feature engineering processing on the first processed data to obtain corresponding second processed data; Performing format conversion processing on the second processed data to obtain corresponding third processed data; The third processed data is used as the target lighting brightness requirement data.

5. The method according to claim 1, characterized in that The preprocessing of the lighting brightness requirement data to obtain corresponding target lighting brightness requirement data includes: Get the preset mapping function; Performing data mapping processing on the lighting brightness prediction result based on the mapping function to obtain mapping data corresponding to the lighting brightness prediction result; The mapping data is used as the target brightness level.

6. The method according to claim 1, characterized in that After obtaining the lighting brightness requirement data in the target area of ​​the airport collected by the preset sensor, the method further includes: Acquire the position movement information of the target passenger in the target area; wherein the movement information includes position information and movement direction information; Get the preset brightness adjustment strategy; Determining a target lighting fixture corresponding to the position movement information; Based on the brightness adjustment strategy, corresponding brightness adjustment processing is performed on the target lighting fixture.

7. The method according to claim 1, characterized in that After the preset control interface sends the brightness adjustment instruction to the lighting device actuator in the target area to control the lighting device actuator to perform corresponding brightness adjustment processing on the lighting fixtures in the target area according to the brightness adjustment instruction, the method further includes: Monitoring working state parameters of lighting fixtures within the target area based on target sensors; Performing data analysis on the working status parameters to determine whether the lighting fixture has a fault; If so, generating warning information corresponding to the fault; Obtaining a solution corresponding to the fault; The warning information and the solution are sent to a preset maintenance personnel.

8. An airport lighting control device based on artificial intelligence, characterized in that: include: A first acquisition module is used to acquire lighting brightness demand data in a target area of ​​an airport collected based on a preset sensor; wherein the lighting brightness demand data at least includes ambient light intensity data, temperature data, humidity data, and passenger flow data; A preprocessing module, used to preprocess the lighting brightness requirement data to obtain corresponding target lighting brightness requirement data; The first calling module is used to call the pre-trained lighting demand prediction model; A prediction module, used to perform prediction processing on the target lighting brightness demand data based on the lighting demand prediction model to obtain a corresponding lighting brightness prediction result; A mapping module, used to convert the lighting brightness prediction result into a corresponding target brightness level based on a preset mapping rule; A first generating module, configured to generate a corresponding brightness adjustment instruction based on the target brightness level; The first sending module is used to send the brightness adjustment instruction to the lighting device actuator in the target area based on a preset control interface, so as to control the lighting device actuator to perform corresponding brightness adjustment processing on the lighting fixtures in the target area according to the brightness adjustment instruction.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the airport lighting control method based on artificial intelligence 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 a computer program, and when the computer program is executed by a processor, the steps of the artificial intelligence-based airport lighting control method according to any one of claims 1 to 7 are implemented.