Multifunctional traffic baton function test method and system based on intelligent sensor

Abstract

The invention discloses a multifunctional traffic baton function test method and system based on an intelligent sensor, and relates to the field of data processing. The method comprises the following steps: extracting a first historical record in historical ambient light intensity records; an ambient light intensity prediction model is obtained and integrated to the traffic baton; obtaining real-time ambient light influence characteristic parameters, and inputting the real-time ambient light influence characteristic parameters into the ambient light intensity prediction model to obtain real-time predicted ambient light intensity; and acquiring the actual ambient light intensity of the traffic baton, and comparing to obtain an ambient light intensity difference. By adopting the method, the technical problems that a traditional traffic baton is greatly influenced by weather conditions, cannot meet traffic guidance requirements in a complex environment, cannot automatically adjust the brightness or color according to the change of the ambient light intensity, and is relatively low in intelligent degree are solved, and the intelligent level of the traffic baton is evaluated, so that the traffic guidance requirement is met. The technical effect of more efficient traffic guidance is achieved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to a method and system for testing the functionality of a multifunctional traffic baton based on intelligent sensors. Background Technology

[0002] With the continuous development of urban traffic, traffic batons, as an important tool for traffic police to direct traffic on the road, directly affect the efficiency and safety of traffic control. Currently, multi-functional traffic batons have become the mainstream product on the market. They not only possess basic command functions but also integrate lighting, warning, and other functions to adapt to different traffic environments. However, traditional traffic batons are limited in function, only usable in well-lit conditions, and greatly affected by weather conditions, failing to meet the needs of traffic control in complex environments. While existing multi-functional traffic batons integrate multiple functions, their level of intelligence is low, unable to automatically adjust brightness or color according to changes in ambient light intensity, resulting in unsatisfactory command effects in certain situations.

[0003] In summary, traditional traffic control batons are greatly affected by weather conditions, cannot meet the traffic control needs in complex environments, and cannot automatically adjust brightness or color according to changes in ambient light intensity, resulting in a low level of intelligence. Summary of the Invention

[0004] Therefore, it is necessary to provide a functional testing method and system for multifunctional traffic batons based on intelligent sensors to address the aforementioned technical problems. This method can solve the technical problems of traditional traffic batons being greatly affected by weather conditions, unable to meet the traffic control needs in complex environments, unable to automatically adjust brightness or color according to changes in ambient light intensity, and having a low level of intelligence. The method will evaluate the intelligence level of the traffic baton, including whether it can automatically adjust brightness or color according to changes in ambient light intensity, and whether it can be linked with other traffic management systems to achieve a more efficient traffic control effect.

[0005] Firstly, a method for testing the functionality of a multifunctional traffic baton based on intelligent sensors is provided, comprising: extracting a first historical record from historical ambient light intensity records, the first historical record including a first historical ambient light influence parameter and a first historical ambient light intensity; performing machine learning on a first data set composed of the first historical ambient light influence parameter and the first historical ambient light intensity to obtain an ambient light intensity prediction model, and integrating the ambient light intensity prediction model into the traffic baton; monitoring the multi-dimensional ambient light influence characteristics of the traffic baton to obtain real-time ambient light influence characteristic parameters, and inputting the real-time ambient light influence characteristic parameters into the ambient light intensity prediction model to obtain real-time predicted ambient light intensity; obtaining the actual ambient light intensity of the traffic baton, and comparing the actual ambient light intensity with the real-time predicted ambient light intensity to obtain the ambient light intensity difference; wherein, the real-time predicted ambient light intensity is used to perform light-adaptive predictive compensation control on the traffic baton, and the ambient light intensity difference is used to characterize the control accuracy of the light-adaptive predictive compensation control of the traffic baton.

[0006] Secondly, a multifunctional traffic baton functional testing system based on intelligent sensors is provided, comprising: a data extraction module for extracting a first historical record from historical ambient light intensity records, the first historical record including a first historical ambient light influence parameter and a first historical ambient light intensity; a model integration module for performing machine learning on a first data set composed of the first historical ambient light influence parameter and the first historical ambient light intensity to obtain an ambient light intensity prediction model, and integrating the ambient light intensity prediction model into the traffic baton; an intensity prediction module for monitoring the multi-dimensional ambient light influence characteristics of the traffic baton to obtain real-time ambient light influence characteristic parameters, and inputting the real-time ambient light influence characteristic parameters into the ambient light intensity prediction model to obtain real-time predicted ambient light intensity; and an intensity difference calculation module for obtaining the actual ambient light intensity of the traffic baton and comparing the actual ambient light intensity with the real-time predicted ambient light intensity to obtain the ambient light intensity difference; wherein, the real-time predicted ambient light intensity is used to perform light-adaptive predictive compensation control on the traffic baton, and the ambient light intensity difference is used to characterize the control accuracy of the light-adaptive predictive compensation control of the traffic baton.

[0007] The aforementioned functional testing method and system for multi-functional traffic batons based on intelligent sensors addresses the technical problems of traditional traffic batons, such as their susceptibility to weather conditions, inability to meet traffic control needs in complex environments, and lack of automatic brightness or color adjustment based on ambient light intensity, resulting in low levels of intelligence. This method evaluates the intelligence level of the traffic baton, including its ability to automatically adjust brightness or color according to changes in ambient light intensity and its ability to integrate with other traffic management systems to achieve more efficient traffic control. The functional testing method and system for multi-functional traffic batons based on intelligent sensors aims to comprehensively evaluate the performance of traffic batons, ensuring they meet the needs of traffic control in complex environments and improving the efficiency and safety of traffic control. Through this testing method, high-performance, fully functional multi-functional traffic batons can be selected, providing strong support for urban traffic management.

[0008] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0009] Figure 1 This is a flowchart illustrating a functional testing method for a multifunctional traffic baton based on smart sensors in one embodiment.

[0010] Figure 2 This is a schematic diagram illustrating the process of obtaining the first target prediction intensity in a multifunctional traffic baton function test method based on smart sensors in one embodiment.

[0011] Figure 3 This is a schematic diagram of the structure of a multifunctional traffic baton functional testing system based on smart sensors in one embodiment.

[0012] Figure labeling: Data extraction module 11, model integration module 12, intensity prediction module 13, intensity difference calculation module 14. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0014] like Figure 1 As shown, this application provides a functional testing method for a multifunctional traffic baton based on intelligent sensors, including: Extract the first historical record from the historical ambient light intensity records. The first historical record includes the first historical ambient light influence parameters and the first historical ambient light intensity.

[0015] A multi-functional traffic baton is a traffic control tool with multiple functions, primarily used for traffic control, evacuation guidance, and signal transmission. It is particularly suitable for use at night, in low-light conditions such as rain, snow, or fog, helping traffic police better direct traffic, warn passing vehicles, and enforce traffic violations. Using LEDs as the light source, it operates primarily through flashing or constant illumination, and its lights are visible from 1000 meters away at night, providing crucial support for traffic safety. Control performance testing refers to a series of processes that evaluate and test the performance of the control system to ensure that the multi-functional traffic baton meets the expected functional and performance requirements. This application provides a functional testing method for a multi-functional traffic baton based on intelligent sensors, conducting a comprehensive and systematic evaluation and testing of the multi-functional traffic baton to ensure that it can stably and reliably perform its traffic control functions in practical use.

[0016] Determine the specific location where historical ambient light intensity records are stored, such as a database table, file path, or in-memory data structure. If the data is stored in a database, connect to the database using an appropriate database connection tool or library; if the data is stored in a file, open the file using file I / O operations. If the data is stored in an in-memory data structure, access the data structure directly. For a database, write an SQL query to retrieve the first record. Typically, this will be the first record after sorting by timestamp or record ID. For a file, if the data is stored row-wise or in a specific format, read the first row or the first data block. For an in-memory data structure, access the first element directly. Parse the queried or retrieved data into the desired format. If the data is JSON, XML, or other structured formats, use the appropriate parsing library or tool. Extract the first historical ambient light influence parameters and the first historical ambient light intensity from the parsed data. These parameters and intensities may be different fields or attributes in the record. The extracted first historical record (including the first historical ambient light influence parameter and the first historical ambient light intensity) is returned to the caller or stored in variables for later use. The historical ambient light intensity record is a series of stored data about the ambient light intensity at a specific point in time or within a time period. This data may include the date, timestamp, specific ambient light intensity value, and other parameters that may be associated with it. The first historical record refers to the earliest record in the historical ambient light intensity record, i.e., the first data in chronological order. This typically represents the starting point or baseline in the record set. The first historical ambient light influence parameter is a parameter associated with the ambient light intensity value in the first historical record; it may be a factor affecting ambient light intensity, such as weather or season. The first historical ambient light intensity refers to the specific ambient light intensity value recorded in the first historical record, usually a numerical value representing the intensity or brightness of the light. Extracting the first historical record provides a baseline for analysis. By understanding the ambient light intensity at the starting moment and its influencing factors, it is easier to compare and evaluate the trends and influencing factors of subsequent records.

[0017] A machine learning model is obtained by performing machine learning on the first data set composed of the first historical ambient light influence parameters and the first historical ambient light intensity, and the ambient light intensity prediction model is integrated into the traffic control stick.

[0018] In addition to the first historical data, more historical ambient light impact parameters and ambient light intensity data need to be collected to build a more comprehensive dataset. The completeness and accuracy of the data should be checked, and missing values ​​and outliers should be handled. Features related to ambient light intensity should be extracted or created based on business needs and data characteristics. Appropriate machine learning algorithms, such as linear regression, decision trees, random forests, and neural networks, should be selected based on the nature of the problem and the characteristics of the data. Historical data should be used as a training set to train the model, and the model parameters should be continuously adjusted to achieve optimal predictive performance. A separate validation set should be used to evaluate the model's performance, such as accuracy, precision, recall, and F1 score. Based on the validation results, the model parameters should be adjusted, and different feature combinations should be tried to optimize the model's performance and obtain an ambient light intensity prediction model. The traffic control baton should be equipped with the ability to receive and process the output of the prediction model. The trained prediction model should be integrated into the traffic control baton's software system, enabling the baton to read ambient light impact parameters and predict ambient light intensity in real time. Based on the real-time read ambient light impact parameters, the traffic control baton should use the prediction model to predict ambient light intensity and adjust its behavior or issue corresponding instructions based on the prediction results. By predicting ambient light intensity, traffic batons can automatically adjust their brightness and color to adapt to different lighting conditions, improving visibility and safety for road users.

[0019] A predetermined influence dimension is read, and the first historical ambient light influence parameter is traversed based on the predetermined influence dimension to obtain a first historical traversal result, which includes multiple dimension parameter groups of multiple influence dimensions; a first dimension parameter group of the first influence dimension is matched among the multiple dimension parameter groups, where the first influence dimension is any one of the multiple influence dimensions; the first dimension parameter group after weighted normalization is used to obtain the first historical dimension influence index of the first influence dimension; the first data group is constructed based on the first historical dimension influence index and the first historical ambient light intensity.

[0020] Identify which factors (i.e., influencing dimensions) affect ambient light intensity. These influencing dimensions may include weather conditions, season, time (e.g., sunrise and sunset times), geographical location (e.g., latitude and longitude), cloud thickness, etc. Based on the application scenario and actual needs, read or define these predetermined influencing dimensions. Use data from historical ambient light intensity records, especially parameters related to these influencing dimensions (i.e., the first historical ambient light influencing parameters), to iterate through the data. The purpose of this iteration is to extract the specific parameter values ​​for each influencing dimension, forming multiple dimensional parameter groups. Among the multiple dimensional parameter groups obtained through iteration, match all parameter groups under the currently focused first influencing dimension (e.g., weather conditions), i.e., the first dimensional parameter group. These parameter groups contain all possible combinations of parameter values ​​under that influencing dimension. Since different parameters may have different dimensions and ranges, direct comparison or calculation may introduce bias. Therefore, it is necessary to perform weighted normalization on each parameter in the first dimensional parameter group. Weighted normalization can assign different weights to each parameter based on its importance and the actual situation, and transform its value to the same range (e.g., between 0 and 1). After weighted normalization, a comprehensive score for each first-dimensional parameter group is obtained, i.e., the first-historical-dimensional influence index. This index reflects the degree of influence of the parameter group on ambient light intensity under the first influence dimension. The calculated first-historical-dimensional influence index is correlated with the corresponding first-historical ambient light intensity value to form the first data set. This data set contains the ambient light intensity values ​​corresponding to different parameter combinations under a specific influence dimension, providing foundational data for subsequent machine learning modeling.

[0021] The predetermined impact dimensions include natural dimensions, environmental dimensions, and anthropogenic dimensions. The natural dimensions include solar altitude, solar azimuth, and light intensity. The environmental dimensions include topography and vegetation cover. The anthropogenic dimensions include building height, artificial lighting intensity, and air pollution index.

[0022] The predetermined impact dimensions include natural, environmental, and anthropogenic dimensions. Natural dimensions include solar altitude (e.g., the sun's altitude angle in the sky throughout the day); solar azimuth (e.g., the sun's azimuth angle relative to the observation point); and light intensity (e.g., the intensity of direct sunlight). Environmental dimensions include topography (e.g., flatlands, mountains, water bodies); and vegetation cover (e.g., flower beds, bare ground). Anthropogenic dimensions include building height (e.g., the height and distribution of surrounding buildings); artificial lighting intensity (e.g., the brightness of streetlights, billboards, and other lighting equipment); and air pollution indices (e.g., the concentration of pollutants such as PM2.5 and PM10). Parameters related to the above impact dimensions are iterated through historical ambient light intensity records. For each record, the specific parameter values ​​for each dimension are extracted. From the obtained parameters, the first impact dimension of interest (e.g., solar altitude in the natural dimension) is selected, and all parameter groups under this dimension are matched, forming the first dimension parameter group. Since the dimensions and ranges of different parameters may differ, weighted normalization is required. Based on the degree of influence of each parameter on ambient light intensity and the actual situation, different weights are assigned to them, and the parameter values ​​are transformed to the same range (e.g., between 0 and 1). Based on the weighted normalized parameter values, a first historical dimension influence index is calculated. This index reflects the degree of influence of different parameter combinations on ambient light intensity under a specific influence dimension. The calculated first historical dimension influence index is correlated with the corresponding first historical ambient light intensity value to form the first data set. This data set contains the ambient light intensity values ​​corresponding to different parameter combinations under a specific influence dimension. For other influence dimensions, such as the environmental dimension and the human dimension, the above steps are repeated to calculate a historical dimension influence index for each dimension and form a data set with the corresponding ambient light intensity value. Using the constructed multidimensional data set as the training dataset, a machine learning model capable of predicting ambient light intensity can be trained. This model will be able to predict the corresponding ambient light intensity value based on the given influence dimension parameter values. By continuously adjusting the model parameters and optimizing the algorithm, the prediction accuracy and generalization ability of the model can be improved. By integrating the trained model into applications such as traffic control sticks, the ambient light intensity can be predicted in real time based on the real-time acquired influence dimension parameter values. The brightness and color parameters of the traffic control sticks can then be adjusted accordingly to adapt to different lighting conditions, thereby improving the visibility and safety of traffic participants.

[0023] The traffic control stick is subjected to multi-dimensional ambient light impact feature monitoring to obtain real-time ambient light impact feature parameters, and the real-time ambient light impact feature parameters are input into the ambient light intensity prediction model to obtain real-time predicted ambient light intensity.

[0024] Using sensors installed on traffic cones or in the surrounding environment, multiple dimensions affecting ambient light intensity are monitored in real time. These dimensions may include natural dimensions (such as solar altitude, solar azimuth, and cloud thickness), environmental dimensions (such as topography, vegetation cover, and weather conditions), and anthropogenic dimensions (such as building obstruction, artificial lighting intensity, and air pollution index). Real-time ambient light impact characteristic parameters are read and extracted from the sensor equipment. These parameters should accurately reflect the main influencing factors of the current ambient light intensity. The extraction process may require cleaning, transforming, and standardizing the raw data to ensure it meets the input requirements of the prediction model. The extracted real-time ambient light impact characteristic parameters are then fed into a pre-trained ambient light intensity prediction model. This model, built based on historical data and machine learning algorithms, should be able to predict the corresponding ambient light intensity value based on the input characteristic parameters. The prediction model calculates the current real-time predicted ambient light intensity value based on the input real-time ambient light impact characteristic parameters. This predicted value should accurately reflect the actual current ambient light intensity. The real-time predicted ambient light intensity value is then used as input to the traffic cone system to guide the adjustment of parameters such as brightness and color of the traffic cones. Based on the predicted ambient light intensity, the system can automatically adjust the brightness of the traffic control stick to ensure the visibility and safety of traffic participants under different lighting conditions. The system continuously monitors its operation, including real-time monitoring of ambient light influence parameters and the accuracy of predicted ambient light intensity. If a significant deviation is found between the predicted results and the actual situation, the prediction model can be adjusted and optimized to improve its accuracy. Simultaneously, user feedback and system operation data can be collected to evaluate the performance and effectiveness of the prediction model, providing a basis for future improvements. Through this process, the traffic control stick system can monitor ambient light influence characteristics in real time and use machine learning models to predict ambient light intensity, thereby automatically adjusting the stick's parameters to adapt to different lighting conditions and improve the visibility and safety of traffic participants.

[0025] The actual ambient light intensity of the traffic control stick is obtained, and the difference between the actual ambient light intensity and the real-time predicted ambient light intensity is compared.

[0026] One or more ambient light sensors are integrated into the traffic control system to monitor and record the actual ambient light intensity at the current location in real time. These sensors can measure light intensity across different wavelength ranges and convert it into a processable digital signal. The data acquired from the ambient light sensors undergoes necessary processing and calibration. This may include noise removal, smoothing, and conversion to a uniform unit of measurement to ensure data accuracy and consistency. As mentioned earlier, a real-time predicted ambient light intensity value is obtained through a multi-dimensional ambient light influence feature monitoring and prediction model. The real-time predicted ambient light intensity value is compared with the actual ambient light intensity value. This can be achieved by comparing the two values ​​at the same point in time. The difference between the predicted and actual ambient light intensity is calculated, i.e., the ambient light intensity difference. This difference can be an absolute difference or a relative difference (such as a percentage difference). The accuracy of the prediction model is evaluated based on the calculated ambient light intensity difference. If the difference is small, the prediction model accurately reflects changes in actual ambient light intensity; if the difference is large, further adjustments and optimizations to the prediction model may be necessary. The ambient light intensity difference is used as a feedback signal to guide the optimization of the prediction model. By analyzing the causes of prediction errors, model parameters can be adjusted, feature selection improved, or new influencing factors introduced to enhance prediction accuracy. Continuous monitoring of the traffic control system's operation is crucial, including monitoring actual ambient light intensity, evaluating the accuracy of the prediction model, and providing feedback and optimization of prediction errors. Through continuous iteration and improvement, the system can be ensured to predict ambient light intensity accurately in real time, providing a reliable basis for the automatic adjustment of traffic control systems.

[0027] A target control performance test time period is obtained, and a first target time is extracted from the target control performance test time period; the real-time predicted ambient light intensity includes real-time time and predicted intensity; an ambient light intensity prediction time series is generated based on the real-time time and the predicted intensity; the actual ambient light intensity includes the real-time time and the actual intensity, and an ambient light intensity time series is generated based on the real-time time and the actual intensity; based on the first target time, the ambient light intensity prediction time series and the ambient light intensity time series are sequentially traversed and matched to obtain the first target predicted intensity and the first target actual intensity, respectively; the intensity deviation between the first target predicted intensity and the first target actual intensity is recorded as the ambient light intensity difference.

[0028] Determine a time period for testing the traffic control baton's performance. This period should be long enough to cover data under different ambient light conditions. Within this target control performance testing period, select one or more specific time points as the first target time. These time points can be fixed (e.g., every hour on the hour) or dynamically selected based on a specific condition (e.g., triggered by a light intensity change threshold). Real-time predicted ambient light intensity data includes real-time time and predicted intensity. Combine each predicted time point and its corresponding predicted intensity into a data pair to form an ambient light intensity prediction time series. Actual ambient light intensity data also includes real-time time and actual intensity. Using actual data acquired from ambient light sensors, combine each measured time point and its corresponding actual intensity into a data pair to form an ambient light intensity time series. Based on the first target time, iterate and match within both the ambient light intensity prediction time series and the ambient light intensity time series to find the data pair closest to (or identical to) the first target time. These data pairs contain the first target predicted intensity and the first target actual intensity, respectively. Compare the first target predicted intensity and the first target actual intensity, and calculate the intensity deviation between them. This deviation can be an absolute difference (i.e., the difference between the two) or a relative difference (e.g., a percentage difference). This intensity deviation is the ambient light intensity difference. Through the steps described above, the performance of the ambient light intensity prediction model in the traffic control system can be systematically evaluated, and reliable data support can be provided for model optimization.

[0029] like Figure 2 As shown, it is determined whether the first target time is included in the ambient light intensity prediction time series; if it is not included in the ambient light intensity prediction time series, a first trend analysis command is issued; based on the first trend analysis command, a trend analysis is performed on the ambient light intensity prediction time series to obtain a first target prediction result; the first target prediction result is recorded as the first target prediction intensity under the first target time.

[0030] Check if the ambient light intensity prediction time series directly contains the predicted intensity data for the first target time point. This can typically be achieved by comparing timestamps or time ranges. If the first target time is not in the prediction time series, issue a first trend analysis command to trigger trend analysis of the ambient light intensity prediction time series. Analyze the ambient light intensity prediction time series using trend analysis algorithms or models. This analysis usually involves finding the prediction data points closest to the first target time and estimating the predicted intensity for the first target time based on the time-intensity relationship of these data points. Trend analysis can use various methods, such as linear interpolation, polynomial fitting, and machine learning model prediction. The choice of method depends on the nature of the data, available computational resources, and the required accuracy. Based on the trend analysis, estimate the predicted intensity for the first target time point; this is the first target prediction result. Use the first target prediction result as the first target predicted intensity for the first target time for subsequent comparisons and analyses. Obtain the first target predicted intensity for the first target time, compare it with the actual ambient light intensity for the first target time, calculate the ambient light intensity difference, and evaluate the performance of the prediction model accordingly. In this way, even if the first target time is not in the ambient light intensity prediction time series, its predicted intensity can still be estimated through trend analysis, thereby maintaining the continuity and accuracy of the test.

[0031] Determine whether the first target time is included in the ambient light intensity time series; if it is not included in the ambient light intensity time series, issue a second trend analysis command; perform trend analysis on the ambient light intensity time series based on the second trend analysis command to obtain a second target prediction result; record the second target prediction result as the actual intensity of the first target under the first target time.

[0032] The process involves checking if the ambient light intensity time series includes the actual intensity data for the first target time point. If the first target time is not included in the time series, a second trend analysis command is issued to trigger trend analysis of the ambient light intensity time series. A trend analysis algorithm or model is used to analyze the ambient light intensity time series. The actual intensity data point closest to the first target time is found, and the actual intensity for the first target time is estimated based on the time-intensity relationship of these data points. Trend analysis is typically used to predict future data points, not to estimate past data points. However, in this case, trend analysis can be viewed as a data interpolation method to fill in data gaps. Based on the trend analysis, the actual intensity for the first target time point is estimated; this is the second target prediction result. Note that this prediction result is actually an estimate of the actual intensity, not a true prediction. The second target prediction result is used as the actual intensity of the first target at the first target time, but this is an estimate, not a true measurement. Ambient light intensity time series is a crucial data source for understanding and analyzing system performance, environmental changes, and traffic conditions. When data is missing at certain time points, estimation through trend analysis can maintain data integrity, thereby avoiding bias in the analysis or decision-making process. By estimating missing data points, biases caused by incomplete data can be avoided during the analysis process, thereby improving the accuracy of the analysis. Decisions based on complete and continuous datasets are generally more reliable than those based on incomplete or discontinuous datasets. Estimating missing data through trend analysis can enhance the reliability of the decision-making process.

[0033] Based on the first trend analysis command, the ambient light intensity prediction scatter plot of the ambient light intensity prediction time series is regressed and fitted to obtain a first fitting polynomial; the first target time is input into the first fitting polynomial to obtain the first target prediction result.

[0034] Ambient light intensity prediction time series data is acquired, typically in the form of timestamps and corresponding predicted light intensity values. These data points can be plotted as a scatter plot, with time on the horizontal axis and light intensity on the vertical axis. When the system or user determines that trend analysis is needed, a first trend analysis command is issued. This command triggers subsequent data analysis and modeling processes. Upon receiving the command, the system performs regression fitting on the scatter plot of ambient light intensity prediction time series. Regression fitting is a statistical method used to determine the relationship between two or more variables. In this case, the relationship between time and light intensity needs to be determined. Various regression models can be selected, such as linear regression, polynomial regression, and nonlinear regression. Since changes in ambient light intensity can be influenced by multiple factors, and these factors may interact, causing light intensity to change nonlinearly over time, polynomial regression may be a suitable choice. Polynomial regression describes the relationship between data points by fitting a polynomial function. After deciding to use polynomial regression, the next step is to solve for the coefficients of the polynomial. This is usually achieved using the least squares method, i.e., finding a set of coefficients that minimizes the sum of squared errors between the fitted polynomial function and the data points. Once the coefficients of the polynomial are solved, the first fitting polynomial can be obtained. This polynomial function can be used to predict the light intensity value at any point in time. Substituting the first target time (i.e., the time point where the light intensity is to be predicted) into the first fitting polynomial yields the predicted light intensity value at that time point, i.e., the first target prediction result. The first target prediction result can be used in various scenarios, such as system monitoring, decision support, and anomaly detection. By comparing the prediction results with the actual measurement results, the accuracy of the prediction model can be evaluated, and the model can be fine-tuned accordingly. Regression fitting of the scatter plot of the ambient light intensity prediction time series based on the first trend analysis instruction, and obtaining the first target prediction result, is a process combining data analysis, mathematical modeling, and prediction techniques. This process allows for a better understanding of the changing patterns of ambient light intensity, enabling more accurate predictions and decisions.

[0035] Based on the second trend analysis instruction, multi-domain features are collected from the ambient light intensity time series to obtain a first multi-domain feature set; the first multi-domain feature set is used as input information for the intensity prediction model to obtain the output result, and the output result is recorded as the second target prediction result; wherein, the intensity prediction model refers to an intelligent prediction model trained based on the principle of neural networks.

[0036] Upon receiving the second trend analysis instruction, the system first performs multi-domain feature collection on the ambient light intensity time series. This typically means extracting light intensity-related features from different dimensions or domains, such as time features, environmental features, geographical location features, and historical light intensity features. These features collectively constitute the first multi-domain feature set, providing rich information for the subsequent prediction model. Before inputting the features into the prediction model, some preprocessing steps are usually required to ensure data quality and model effectiveness. This may include data cleaning (removing outliers, missing values, etc.), data standardization or normalization, and feature encoding (such as converting categorical variables into numerical variables). In this scenario, the intensity prediction model is an intelligent prediction model trained based on neural network principles. Neural network models have strong nonlinear fitting capabilities and can handle complex nonlinear relationships, thus finding wide application in time series prediction. During training, this model has learned the complex relationships between ambient light intensity and various features. Therefore, when a new feature set (i.e., the first multi-domain feature set) is input into the model, the model can output a predicted light intensity value based on these features. The model output is the second target prediction result, which represents the predicted ambient light intensity value at the first target time point. This prediction value is obtained based on a multi-domain feature set and a trained neural network model, thus possessing high accuracy and reliability. Collecting multi-domain features of ambient light intensity time series based on the second trend analysis instruction and using an intelligent prediction model based on neural network principles is an efficient and accurate method that can help better understand and predict the changing patterns of ambient light intensity.

[0037] The real-time predicted ambient light intensity is used to perform light-adaptive predictive compensation control on the traffic control stick, and the ambient light intensity difference is used to characterize the control accuracy of the light-adaptive predictive compensation control of the traffic control stick.

[0038] Real-time prediction of ambient light intensity and corresponding light-adaptive predictive compensation control of traffic batons is a crucial task. This control strategy aims to ensure that traffic batons provide clear and visible visual indications under varying lighting conditions, thereby enhancing traffic safety. Real-time prediction of ambient light intensity is achieved by collecting and analyzing current ambient light data. This data may come from multiple sensors, such as photoresistors and photometers, which measure and report real-time changes in ambient light intensity. By processing and analyzing this data, the trend of ambient light intensity changes over a future period can be predicted. Light-adaptive predictive compensation control is a control strategy that adjusts the brightness and color of traffic batons based on real-time predicted ambient light intensity. The purpose of this strategy is to ensure that traffic batons provide sufficient brightness and contrast under different lighting conditions so that drivers can clearly see the baton's indications. Specifically, when the ambient light intensity is low, light-adaptive predictive compensation control increases the brightness of the traffic batons to make them more conspicuous; while when the ambient light intensity is high, it appropriately reduces the brightness to avoid excessive glare that may interfere with drivers. Furthermore, the control strategy can adjust the color of the traffic baton based on changes in ambient light intensity to provide better visual guidance under specific conditions (such as foggy days or nighttime). The ambient light intensity difference refers to the difference between the actual ambient light intensity and the predicted ambient light intensity. This difference can be used to characterize the control accuracy of light-adaptive predictive compensation control. Specifically, if the ambient light intensity difference is small, it indicates that the prediction model has high accuracy, and the control strategy can accurately adjust the brightness and color of the traffic baton according to changes in ambient light intensity; conversely, if the ambient light intensity difference is large, it indicates that the prediction model has low accuracy, and the control strategy may not be able to accurately adapt to changes in ambient light intensity.

[0039] For specific embodiments of the functional testing method for the multifunctional traffic baton based on intelligent sensors, please refer to the above. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0040] Example 2: Based on the same inventive concept as the multifunctional traffic baton function testing method based on intelligent sensors in Example 1, this application also provides a multifunctional traffic baton function testing system based on intelligent sensors. Please refer to the appendix. Figure 3The multifunctional traffic baton functional testing system based on intelligent sensors includes: a data extraction module 11, used to extract a first historical record from historical ambient light intensity records, the first historical record including a first historical ambient light influence parameter and a first historical ambient light intensity; a model integration module 12, used to perform machine learning on a first data set composed of the first historical ambient light influence parameter and the first historical ambient light intensity to obtain an ambient light intensity prediction model, and integrate the ambient light intensity prediction model into the traffic baton; an intensity prediction module 13, used to monitor the multi-dimensional ambient light influence characteristics of the traffic baton to obtain real-time ambient light influence characteristic parameters, and input the real-time ambient light influence characteristic parameters into the ambient light intensity prediction model to obtain real-time predicted ambient light intensity; and an intensity difference calculation module 14, used to obtain the actual ambient light intensity of the traffic baton and compare the actual ambient light intensity with the real-time predicted ambient light intensity to obtain the ambient light intensity difference; wherein, the real-time predicted ambient light intensity is used to perform light-adaptive predictive compensation control on the traffic baton, and the ambient light intensity difference is used to characterize the control accuracy of the light-adaptive predictive compensation control of the traffic baton.

[0041] Furthermore, the multifunctional traffic control baton function testing system based on intelligent sensors also includes: reading a predetermined influence dimension, and traversing the first historical ambient light influence parameters based on the predetermined influence dimension to obtain a first historical traversal result, the first historical traversal result including multiple dimension parameter groups of multiple influence dimensions; matching the first dimension parameter group of the first influence dimension in the multiple dimension parameter groups, the first influence dimension being any one of the multiple influence dimensions; obtaining the first historical dimension influence index of the first influence dimension after weighted normalization of the first dimension parameter group; and constructing the first data group based on the first historical dimension influence index and the first historical ambient light intensity.

[0042] Furthermore, the multifunctional traffic control baton function testing system based on intelligent sensors also includes: the predetermined influence dimensions include natural dimensions, environmental dimensions, and human dimensions, the natural dimensions include solar altitude, solar azimuth, and light intensity, the environmental dimensions include topography and vegetation cover, and the human dimensions include building height, artificial lighting intensity, and air pollution index.

[0043] Furthermore, the multifunctional traffic control baton function testing system based on intelligent sensors also includes: acquiring a target control performance test time period and extracting a first target time from the target control performance test time period; the real-time predicted ambient light intensity includes real-time time and predicted intensity; generating an ambient light intensity prediction time series based on the real-time time and the predicted intensity; the actual ambient light intensity includes the real-time time and the actual intensity, and generating an ambient light intensity time series based on the real-time time and the actual intensity; sequentially traversing and matching the ambient light intensity prediction time series and the ambient light intensity time series based on the first target time to obtain a first target predicted intensity and a first target actual intensity respectively; and recording the intensity deviation between the first target predicted intensity and the first target actual intensity as the ambient light intensity difference.

[0044] Furthermore, the multifunctional traffic baton function testing system based on intelligent sensors also includes: determining whether the first target time is included in the ambient light intensity prediction time series; if it is not included in the ambient light intensity prediction time series, issuing a first trend analysis command; performing trend analysis on the ambient light intensity prediction time series based on the first trend analysis command to obtain a first target prediction result; and recording the first target prediction result as the first target prediction intensity under the first target time.

[0045] Furthermore, the multifunctional traffic baton function testing system based on intelligent sensors also includes: determining whether the first target time is included in the ambient light intensity time series; if it is not included in the ambient light intensity time series, issuing a second trend analysis command; performing trend analysis on the ambient light intensity time series based on the second trend analysis command to obtain a second target prediction result; and recording the second target prediction result as the actual intensity of the first target under the first target time.

[0046] Furthermore, the multifunctional traffic control stick function testing system based on intelligent sensors also includes: performing regression fitting on the ambient light intensity prediction scatter plot of the ambient light intensity prediction time series based on the first trend analysis command to obtain a first fitting polynomial; inputting the first target time into the first fitting polynomial to obtain the first target prediction result.

[0047] Furthermore, the multi-functional traffic baton function testing system based on intelligent sensors also includes: collecting multi-domain features of the ambient light intensity time series based on the second trend analysis command to obtain a first multi-domain feature set; using the first multi-domain feature set as input information of the intensity prediction model to obtain the output result, and recording the output result as the second target prediction result; wherein, the intensity prediction model refers to an intelligent prediction model trained based on the principle of neural networks.

[0048] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The functional testing method and specific examples of the multi-functional traffic baton based on intelligent sensors in the aforementioned embodiment one are also applicable to the functional testing system of the multi-functional traffic baton based on intelligent sensors in this embodiment.

[0049] The embodiments described above are merely examples of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application.

Claims

1. A method for testing the functionality of a multifunctional traffic controller based on intelligent sensors, characterized in that, include: Extract the first historical record from the historical ambient light intensity record, the first historical record including the first historical ambient light influence parameter and the first historical ambient light intensity; Machine learning is performed on the first data set composed of the first historical ambient light influence parameters and the first historical ambient light intensity to obtain an ambient light intensity prediction model, and the ambient light intensity prediction model is integrated into the traffic control stick; Multi-dimensional ambient light impact characteristics are monitored on the traffic control stick to obtain real-time ambient light impact characteristic parameters. The real-time ambient light impact characteristic parameters are then input into the ambient light intensity prediction model to obtain the real-time predicted ambient light intensity. The actual ambient light intensity of the traffic control stick is obtained, and the difference between the actual ambient light intensity and the real-time predicted ambient light intensity is compared. The real-time predicted ambient light intensity is used to perform light-adaptive predictive compensation control on the traffic control stick, and the ambient light intensity difference is used to characterize the control accuracy of the light-adaptive predictive compensation control of the traffic control stick.

2. The functional testing method for the multifunctional traffic controller based on intelligent sensors according to claim 1, characterized in that, include: Read the predetermined influence dimension, and iterate through the first historical ambient light influence parameter based on the predetermined influence dimension to obtain the first historical traversal result. The first historical traversal result includes multiple dimension parameter groups of multiple influence dimensions. Match the first dimension parameter group of the first influence dimension in the plurality of dimension parameter groups, wherein the first influence dimension is any one of the plurality of influence dimensions; The first dimension parameter group after weighted normalization is used to obtain the first historical dimension influence index of the first influence dimension. The first data group is constructed based on the first historical dimension influence index and the first historical ambient light intensity.

3. The functional testing method for the multifunctional traffic controller based on intelligent sensors according to claim 2, characterized in that, The predetermined impact dimensions include natural dimensions, environmental dimensions, and anthropogenic dimensions. The natural dimensions include solar altitude, solar azimuth, and light intensity. The environmental dimensions include topography and vegetation cover. The anthropogenic dimensions include building height, artificial lighting intensity, and air pollution index.

4. The functional testing method for the multifunctional traffic controller based on intelligent sensors according to claim 1, characterized in that, include: Obtain the target control performance test period and extract the first target time from the target control performance test period; The real-time predicted ambient light intensity includes real-time time and predicted intensity; Ambient light intensity prediction time series is generated based on the real-time time and the predicted intensity; The actual ambient light intensity includes the real-time time and the actual intensity, and an ambient light intensity time series is generated based on the real-time time and the actual intensity; Based on the first target time, the ambient light intensity prediction time series and the ambient light intensity time series are sequentially matched to obtain the first target prediction intensity and the first target actual intensity, respectively. The intensity deviation between the predicted intensity of the first target and the actual intensity of the first target is denoted as the ambient light intensity difference.

5. The functional testing method for the multifunctional traffic controller based on intelligent sensors according to claim 4, characterized in that, Also includes: Determine whether the first target time is included in the ambient light intensity prediction time series; If it is not included in the ambient light intensity prediction timeline, issue a first trend analysis command; Based on the first trend analysis command, a trend analysis is performed on the ambient light intensity prediction time series to obtain the first target prediction result; The prediction result of the first target is recorded as the prediction intensity of the first target at the first target time.

6. The functional testing method for the multifunctional traffic baton based on intelligent sensors according to claim 4, characterized in that, Also includes: Determine whether the first target time is included in the ambient light intensity time series; If it is not included in the ambient light intensity time series, issue a second trend analysis command; Based on the second trend analysis command, the ambient light intensity time series is analyzed to obtain the second target prediction result; The second target prediction result is recorded as the actual intensity of the first target at the first target time.

7. The functional testing method for the multifunctional traffic baton based on intelligent sensors according to claim 5, characterized in that, include: Based on the first trend analysis command, a regression fitting is performed on the scatter plot of ambient light intensity prediction time series to obtain a first fitting polynomial; The first target time is input into the first fitting polynomial to obtain the first target prediction result.

8. The functional testing method for the multifunctional traffic controller based on intelligent sensors according to claim 6, characterized in that, include: Based on the second trend analysis command, multi-domain features of the ambient light intensity time series are collected to obtain the first multi-domain feature set; The first multi-domain feature set is used as the input information of the intensity prediction model to obtain the output result, and the output result is recorded as the second target prediction result; The intensity prediction model refers to an intelligent prediction model trained based on neural network principles.

9. A multifunctional traffic control baton functional testing system based on intelligent sensors, characterized in that, The steps for implementing the functional testing method for the multi-functional traffic baton based on intelligent sensors according to any one of claims 1 to 8, wherein the multi-functional traffic baton functional testing system based on intelligent sensors comprises: The data extraction module is used to extract the first historical record from the historical ambient light intensity record, the first historical record including the first historical ambient light influence parameter and the first historical ambient light intensity; The model integration module is used to perform machine learning on the first data set composed of the first historical ambient light influence parameters and the first historical ambient light intensity to obtain an ambient light intensity prediction model, and to integrate the ambient light intensity prediction model into the traffic control stick; The intensity prediction module is used to monitor the multi-dimensional ambient light impact characteristics of the traffic control stick, obtain real-time ambient light impact characteristic parameters, and input the real-time ambient light impact characteristic parameters into the ambient light intensity prediction model to obtain the real-time predicted ambient light intensity. The intensity difference calculation module is used to obtain the actual ambient light intensity of the traffic control stick and compare it with the ambient light intensity difference between the actual ambient light intensity and the real-time predicted ambient light intensity. The real-time predicted ambient light intensity is used to perform light-adaptive predictive compensation control on the traffic control stick, and the ambient light intensity difference is used to characterize the control accuracy of the light-adaptive predictive compensation control of the traffic control stick.

Images