Laser radar signal enhancement method and system based on artificial intelligence optimization

Abstract

The invention relates to the technical field of artificial intelligence, and particularly provides a laser radar signal enhancement method and system based on artificial intelligence optimization. Multi-dimensional features of original laser radar data, original point cloud detection data and surface performance mapping information are deeply mined and analyzed; according to the scheme, the detection capability of the system on weak echo signals is remarkably improved, and the optimal design of the metasurface structure is realized by integrating the deep learning model. The innovative technical path aims to solve the technical problem that the detection precision and range of a traditional laser radar are limited in a complex environment, and therefore comprehensive progress and wide application of the laser radar technology are promoted.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a laser radar signal enhancement method and system based on artificial intelligence optimization. Background Art

[0002] With the rapid development of science and technology, LiDAR systems are playing an increasingly important role in many fields, such as environmental monitoring and meteorological analysis. However, traditional LiDAR technology often has insufficient detection capabilities when facing weak echo signals, which seriously affects the performance and application scope of the system. Especially under complex and changing environmental conditions, how to ensure the high-sensitivity detection of LiDAR systems has always been a technical problem that the industry needs to solve urgently. Summary of the invention

[0003] In order to improve the above problems, the present application provides a lidar signal enhancement method and system based on artificial intelligence optimization.

[0004] The embodiment of the present application provides a laser radar signal enhancement method based on artificial intelligence optimization, which is applied to a signal enhancement system. The method includes:

[0005] Performing feature vector mining on the original laser radar data to obtain an original signal state monitoring vector of the original laser radar data;

[0006] Performing feature vector mining on the original point cloud detection data corresponding to the original laser radar data to obtain a laser point cloud spatiotemporal linkage vector of the original point cloud detection data;

[0007] Performing feature vector mining on a plurality of original laser radar data segments corresponding to the original laser radar data to obtain a signal-to-noise change trend vector corresponding to each of the original laser radar data segments;

[0008] Performing feature vector mining on a plurality of hypertable structure model data corresponding to the surface performance mapping information to obtain a quantized structural geometric distribution vector corresponding to each group of the hypertable structure model data;

[0009] For each group of the quantized structure geometric distribution vectors, the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, a plurality of the signal-to-noise change trend vectors and the quantized structure geometric distribution vector are subjected to knowledge interaction based on inter-class feature focusing to obtain a signal enhancement comparison vector;

[0010] Structural parameter prediction is performed on a plurality of the signal enhancement comparison vectors to obtain hypersurface geometric parameters that match both the original lidar data and the surface performance mapping information.

[0011] Optionally, performing feature vector mining on a plurality of original laser radar data segments corresponding to the original laser radar data to obtain a signal-to-noise change trend vector corresponding to each of the original laser radar data segments includes:

[0012] For each of the original laser radar data segments, feature vector mining is performed on the original laser radar data segment according to the first knowledge dimension to obtain a first signal quality assessment vector corresponding to the original laser radar data segment;

[0013] Performing feature vector mining on the original laser radar data segment according to the second knowledge dimension to obtain a second signal quality assessment vector corresponding to the original laser radar data segment;

[0014] Knowledge interaction is performed on the first signal quality assessment vector and the second signal quality assessment vector to obtain a signal-to-noise change trend vector corresponding to the original lidar data segment.

[0015] Optionally, the step of obtaining the plurality of original laser radar data segments includes:

[0016] The original laser radar data is disassembled based on a data scanning core to obtain the plurality of original laser radar data segments; each of the original laser radar data segments includes key field indexes of the associated plurality of original laser radar data segments.

[0017] Optionally, the performing feature vector mining on a plurality of hypertable structure model data corresponding to the surface performance mapping information to obtain a quantized structural geometric distribution vector corresponding to each group of the hypertable structure model data includes:

[0018] For each group of the hypertable structure model data, identifying the spatial arrangement state of the hypertable structure model data to obtain a target spatial arrangement state information set corresponding to the hypertable structure model data;

[0019] Feature vector mining is performed on the target space arrangement state information set to obtain the quantitative structure geometric distribution vector corresponding to the hypertable structure model data.

[0020] Optionally, the performing feature vector mining on the target spatial arrangement state information set to obtain the quantized structural geometric distribution vector corresponding to the hypertable structure model data includes:

[0021] Performing knowledge mapping on the target spatial arrangement state information set to obtain a plurality of first spatial arrangement state knowledge corresponding to the target spatial arrangement state information set;

[0022] Performing interval numerical mapping on the plurality of first spatial arrangement state knowledge to obtain second spatial arrangement state knowledge corresponding to each first spatial arrangement state knowledge;

[0023] Performing feature collision on a plurality of pieces of the second spatial arrangement state knowledge to obtain third spatial arrangement state knowledge corresponding to each piece of the second spatial arrangement state knowledge;

[0024] Linearly quantize a plurality of the third spatial arrangement state knowledge to obtain the quantized structure geometric distribution vector.

[0025] Optionally, for each group of the quantized structure geometric distribution vectors, the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, a plurality of the signal-to-noise change trend vectors and the quantized structure geometric distribution vector are subjected to knowledge interaction based on inter-class feature focusing to obtain a signal enhancement comparison vector, including:

[0026] Performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, and a plurality of the signal-to-noise change trend vectors to obtain a first inter-class signal focusing linkage vector;

[0027] For each group of the quantization structure geometric distribution vectors, knowledge interaction is performed on the first inter-class signal focus linkage vector and the quantization structure geometric distribution vector to obtain the signal enhancement comparison vector.

[0028] Optionally, for each group of the quantized structure geometric distribution vectors, the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, a plurality of the signal-to-noise change trend vectors and the quantized structure geometric distribution vector are subjected to knowledge interaction based on inter-class feature focusing to obtain a signal enhancement comparison vector, including:

[0029] Performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, and a plurality of the signal-to-noise change trend vectors to obtain a first inter-class signal focusing linkage vector;

[0030] For each group of the quantized structure geometric distribution vectors, the original signal state monitoring vector and the quantized structure geometric distribution vector are subjected to knowledge interaction based on inter-class feature focusing to obtain a second inter-class signal focusing linkage vector;

[0031] Knowledge interaction is performed on the first inter-class signal focus linkage vector and the second inter-class signal focus linkage vector to obtain the signal enhancement comparison vector.

[0032] Optionally, performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, and a plurality of the signal-to-noise change trend vectors to obtain a first inter-class signal focusing linkage vector includes:

[0033] Performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector and the laser point cloud spatiotemporal linkage vector to obtain a third inter-class signal focusing linkage vector;

[0034] Performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector and the plurality of signal-to-noise change trend vectors to obtain a fourth inter-class signal focusing linkage vector;

[0035] Knowledge interaction is performed on the third inter-class signal focusing linkage vector and the fourth inter-class signal focusing linkage vector to obtain the first inter-class signal focusing linkage vector; the knowledge size of the first inter-class signal focusing linkage vector, the knowledge size of the third inter-class signal focusing linkage vector, and the knowledge size of the fourth inter-class signal focusing linkage vector are the same.

[0036] Optionally, performing knowledge interaction on the first inter-class signal focus linkage vector and the quantization structure geometric distribution vector to obtain the signal enhancement comparison vector includes:

[0037] Performing knowledge interaction based on inter-class feature focusing on the first inter-class signal focusing linkage vector and the quantization structure geometric distribution vector to obtain a target signal quality deduction vector;

[0038] Knowledge interaction is performed on the first inter-class signal focus linkage vector and the target signal quality deduction vector to obtain the signal enhancement comparison vector.

[0039] Optionally, the performing structural parameter prediction on a plurality of the signal enhancement comparison vectors to obtain hypersurface geometric parameters that match both the original laser radar data and the surface performance mapping information includes:

[0040] Performing signal stream integration on a plurality of the signal enhancement comparison vectors to obtain a global inter-class signal focusing linkage vector corresponding to each group of the signal enhancement comparison vectors;

[0041] Structural parameter prediction is performed on a number of the global inter-class signal focusing linkage vectors to obtain the hypersurface geometric parameters.

[0042] Optionally, performing signal stream integration on a plurality of the signal enhancement comparison vectors to obtain a global inter-class signal focusing linkage vector corresponding to each group of the signal enhancement comparison vectors includes:

[0043] Performing clustering processing on the plurality of signal enhancement comparison vectors to obtain a plurality of signal enhancement comparison vectors under a plurality of classification clusters;

[0044] For the plurality of signal enhancement comparison vectors under each classification cluster, signal stream integration is performed on the plurality of signal enhancement comparison vectors under the classification cluster to obtain a global inter-class signal focusing linkage vector corresponding to each group of the signal enhancement comparison vectors under the classification cluster;

[0045] Knowledge interaction is performed on a plurality of the global inter-class signal focusing linkage vectors under a plurality of the classification clusters to obtain a global inter-class signal focusing linkage vector corresponding to each group of the signal enhancement comparison vectors.

[0046] An embodiment of the present application provides a signal enhancement system, comprising at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the above method.

[0047] An embodiment of the present application provides a computer-readable storage medium on which a computer program is stored. The computer program implements the above method when running.

[0048] In the embodiment of this application, by deeply mining and analyzing the multi-dimensional features of the original laser radar data, the original point cloud detection data and the surface performance mapping information, this solution not only significantly improves the system's detection capability for weak echo signals, but also achieves the optimized design of the metasurface structure by integrating the deep learning model. This innovative technical path aims to solve the technical problems of the limited detection accuracy and range of traditional laser radars in complex environments, thereby promoting the overall advancement and widespread application of laser radar technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flowchart of a laser radar signal enhancement method based on artificial intelligence optimization provided in an embodiment of the present application.

[0050] Figure 2 A schematic diagram of the structure of a signal enhancement system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to better understand the above technical scheme, the technical scheme of the present application is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, rather than limitations on the technical scheme of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0052] Figure 1 A laser radar signal enhancement method based on artificial intelligence optimization is shown, which is applied to a signal enhancement system. The method includes the following steps 110-160.

[0053] In the field of meteorological observation, the signal enhancement system involved in the embodiment of the present application plays a vital role. It can deeply process the original lidar data, thereby improving the accuracy and availability of the data. The following is a specific meteorological application scenario, which details how the signal enhancement system implements its technical solution.

[0054] First, the signal enhancement system processes the raw lidar data. In step 110, the signal enhancement system performs feature vector mining on the raw lidar data. The purpose of this step is to extract the core features of the raw lidar data and obtain the raw signal state monitoring vector. The raw signal state monitoring vector can reflect the initial state and quality of the radar signal.

[0055] Next, in step 120, the signal enhancement system further processes the raw point cloud detection data corresponding to the raw laser radar data. By mining the feature vectors of the raw point cloud detection data, the signal enhancement system can obtain the laser point cloud spatiotemporal linkage vector. The laser point cloud spatiotemporal linkage vector reveals the distribution and variation characteristics of the laser radar point cloud data in time and space.

[0056] In step 130, the signal enhancement system continues to analyze the original lidar data, divides it into several data segments, and performs feature vector mining on each data segment. In this way, the signal enhancement system can obtain the signal-to-noise change trend vector corresponding to each data segment, and the signal-to-noise change trend vector reflects the change trend of the signal and noise in different time periods.

[0057] The surface performance mapping information is another important data source. In step 140, the signal enhancement system performs feature mining on several hypertable structure model data contained in the surface performance mapping information to obtain a quantized structural geometric distribution vector of each set of hypertable structure model data. The quantized structural geometric distribution vector describes the geometric characteristics and distribution of the hypersurface structure.

[0058] Entering step 150, the signal enhancement system begins to integrate the various feature vectors previously mined. For each set of quantized structure geometric distribution vectors, the signal enhancement system interacts the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, several signal-to-noise change trend vectors, and the quantized structure geometric distribution vector. This interactive process is based on the principle of inter-class feature focusing, aiming to extract the most representative information and ultimately generate a signal enhancement comparison vector.

[0059] Finally, in step 160, the signal enhancement system uses several signal enhancement comparison vectors to predict structural parameters. Through this step, the signal enhancement system can determine the hypersurface geometric parameters that match the original lidar data and surface performance mapping information. These parameters are crucial to optimizing the radar signal quality and improving the accuracy of meteorological observations.

[0060] Through the above process, the signal enhancement system not only improves the signal-to-noise ratio of lidar data, but also provides more accurate and reliable data support for meteorological observations through the optimization of metasurface geometric parameters.

[0061] Step 110: perform feature vector mining on the original laser radar data to obtain an original signal state monitoring vector of the original laser radar data.

[0062] Step 120: perform feature vector mining on the original point cloud detection data corresponding to the original laser radar data to obtain the laser point cloud spatiotemporal linkage vector of the original point cloud detection data.

[0063] Step 130: perform feature vector mining on a plurality of original laser radar data segments corresponding to the original laser radar data to obtain a signal-to-noise change trend vector corresponding to each of the original laser radar data segments.

[0064] Step 140: Perform feature vector mining on a plurality of hypertable structure model data corresponding to the surface performance mapping information to obtain a quantized structural geometric distribution vector corresponding to each group of the hypertable structure model data.

[0065] Step 150: For each group of the quantized structure geometric distribution vectors, the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, a plurality of the signal-to-noise change trend vectors and the quantized structure geometric distribution vector are subjected to knowledge interaction based on inter-class feature focusing to obtain a signal enhancement comparison vector.

[0066] Step 160: perform structural parameter prediction on a plurality of the signal enhancement comparison vectors to obtain hypersurface geometric parameters that match both the original lidar data and the surface performance mapping information.

[0067] In the above steps 110 to 140, four different feature vector mining are involved. The following first provides an exemplary description of the relevant technical terms.

[0068] Raw lidar data refers to the unprocessed data directly captured by the lidar device. In meteorological observation, lidar detects and measures various particles in the atmosphere (such as water droplets, ice crystals, dust, etc.) by emitting laser beams and receiving the signals reflected back. These data are crucial for analyzing cloud structure, precipitation types, and predicting weather changes. Raw lidar data can contain a lot of noise and interference, and further processing is required to extract useful meteorological information.

[0069] The raw signal state monitoring vector is obtained by mining the feature vector of the raw lidar data. Feature vector mining is a data analysis technique that can extract key features from a large amount of data. In this scenario, the raw signal state monitoring vector reflects the initial state and quality of the radar signal, including key indicators such as signal strength, stability, and noise level. This vector helps to understand the working status of the radar equipment and the environmental conditions for data collection.

[0070] The original point cloud detection data is a collection of points in space obtained by laser radar scanning. Each point contains its coordinates in three-dimensional space and possible information such as color and reflection intensity. In meteorological observation, point cloud data can reveal the shape, thickness, height and internal structural characteristics of clouds. The original point cloud detection data is unprocessed point cloud data directly obtained from the radar equipment.

[0071] The laser point cloud spatiotemporal linkage vector is obtained by mining the feature vector of the original point cloud detection data. This vector captures the distribution and change characteristics of the point cloud data in time and space. For example, it can reveal the movement speed, direction and morphological changes of clouds at different time points, which is crucial for predicting the evolution and movement path of weather systems.

[0072] Raw LiDAR data segmentation refers to cutting continuous raw LiDAR data into several smaller data segments. Each data segment contains radar observation data within a period of time. This segmentation process helps to analyze the local features and change trends in the data in more detail.

[0073] The signal-to-noise change trend vector is obtained by mining the feature vector of each raw lidar data segment, which reflects the change trend of the signal and noise in each data segment. In meteorological observation, the ratio of signal to noise directly affects the accuracy and reliability of the data. The signal-to-noise change trend vector can help understand the change of signal quality in different time periods, thereby optimizing the data processing strategy.

[0074] Surface property mapping information refers to data and information related to the surface properties of radar detection targets (such as clouds, precipitation particles, etc.). Surface properties can include physical properties such as reflectivity, scattering characteristics, and dielectric constant. These properties are crucial to understanding and interpreting radar signals because they directly affect the reflection and propagation behavior of radar waves.

[0075] Hyperstructure model data refers to data that describes the microstructure or morphology of the surface of a radar detection target. In meteorological observations, the microstructure of clouds and precipitation particles (such as the size, shape, and distribution of water droplets) has an important influence on the reflection and scattering of radar signals. Hyperstructure model data provides a mathematical description or simulation of these microstructures, which helps to more accurately interpret radar signals and extract useful meteorological information.

[0076] The quantitative structure geometric distribution vector is obtained by feature mining the hypertable structure model data contained in the surface performance mapping information, and describes the geometric characteristics and distribution of the hypersurface structure. For example, it can represent the size distribution, shape characteristics, and spatial arrangement of water droplets in the cloud layer. This quantitative information is of great significance for understanding the reflection and scattering mechanism of radar signals and improving weather forecast models.

[0077] Based on the above, in step 110, feature vector mining focuses on the overall signal status of the original lidar data. By performing statistical analysis and pattern recognition on the entire data set, the system extracts features that reflect the basic status of the radar signal, such as the average strength of the signal, the fluctuation range, and the stability index. These features are synthesized into a vector - the original signal state monitoring vector, which provides a quick assessment of the overall quality of the radar signal. This mining focuses on the global characteristics of the signal, which helps to understand the basic working performance of the radar system and the overall performance of the signal in the current environment.

[0078] Furthermore, the feature vector mining in step 120 focuses on extracting spatiotemporal dynamic information from the original point cloud detection data. Point cloud data contains rich three-dimensional spatial structure and dynamic change information. Therefore, this step of mining aims to capture the dynamic behavior and spatial distribution pattern of the point cloud. By analyzing the density, shape, motion trajectory and other features of the point cloud, the system generates a spatiotemporal linkage vector of the laser point cloud. This vector not only reflects the distribution state of the point cloud in space, but also reveals its trend over time, which is crucial for understanding and predicting the evolution of weather systems.

[0079] In step 130, the raw lidar data is segmented into multiple data segments to more carefully analyze the local features and change trends of the signal. Feature vector mining here focuses on the stability and noise level of the signal in each data segment. The system generates a signal-to-noise change trend vector for each data segment by detecting fluctuations in signal strength, changes in noise components, etc. This vector reveals the relative changes in signal and noise over different time periods, helps identify outliers and noise interference in the data, and thus improves the accuracy of data processing.

[0080] The feature vector mining in the last step (step 140) focuses on the hypertable structure model data in the surface performance mapping information. These data describe the microstructure and morphology of the radar detection target. By deeply mining the geometric features and spatial distribution patterns of these model data, such as the size, shape, and arrangement of the structure, the system generates a quantitative structural geometric distribution vector. This vector provides an accurate quantitative description of the target surface microstructure, which helps to understand the way the radar signal interacts with the detection target, thereby optimizing the accuracy of signal interpretation and model prediction.

[0081] It can be seen that the feature vector mining in the above four steps has different focuses, from the global signal state to the local signal-noise change, and then to the microstructure characteristics, together forming a comprehensive data analysis framework, providing a rich information basis for meteorological observation and forecasting.

[0082] Based on the above content, knowledge interaction based on inter-class feature focusing focuses on extracting key features from data of different categories, and interacting and fusing these features through specific algorithms. In this process, "inter-class" refers to data of different categories or different sources, such as raw lidar data, point cloud detection data, etc.; "feature focusing" refers to refining and emphasizing the key information in these data. Through this knowledge interaction, a more comprehensive and in-depth understanding of the data can be obtained, thereby providing more accurate information support for subsequent decision-making.

[0083] The signal enhancement comparison vector is a result vector obtained through processing with a specific algorithm. It is mainly used to compare and evaluate the effects of different signal processing methods. In this application scenario, the signal enhancement comparison vector is generated through knowledge interaction based on inter-class feature focusing. It integrates feature information from multiple data sources to highlight the signal enhancement part, making it easier to intuitively understand the improvement in signal quality. This vector can not only help evaluate the effect of signal processing, but also serve as an important basis for subsequent optimization algorithms.

[0084] It can be seen that step 150 is a key link in the entire data processing process. It integrates the results of the previous steps and generates a signal enhancement comparison vector through knowledge interaction based on inter-class feature focusing. In this step, the four key vectors obtained in the previous steps are first reviewed and integrated: the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, the signal-noise change trend vector, and the quantized structure geometric distribution vector. These four vectors characterize the characteristics of radar data and detection targets from different angles, providing a rich information basis. Next, the knowledge interaction technology based on inter-class feature focusing is used to conduct in-depth analysis and fusion of these vectors. In this process, special attention is paid to the correlation and complementarity between different vectors, and efforts are made to mine the inherent laws of data from multiple angles and levels. Through precise algorithm processing, the common features and unique information of these vectors are extracted, and effective knowledge interaction is achieved. Finally, a brand new vector is obtained: the signal enhancement comparison vector. This vector integrates the feature information of multiple data sources, not only comprehensively reflects the overall state of the radar signal, but also highlights the signal enhancement part. By observing and analyzing this vector, the effect of signal processing can be intuitively evaluated, providing strong data support for subsequent optimization work. In general, step 150 is a comprehensive data processing link, which makes full use of the results of the previous steps and provides a comprehensive and in-depth data understanding perspective through knowledge interaction based on inter-class feature focusing. This not only helps to better understand the characteristics of radar data and detected targets, but also lays a solid foundation for subsequent meteorological observation and forecasting work.

[0085] Finally, structural parameter prediction is a technology that infers and predicts future or unknown structural characteristics through specific algorithms or models. In this application scenario, structural parameter prediction specifically refers to the use of data information such as signal enhancement comparison vectors to predict structural parameters related to radar detection targets, such as the shape, size, distribution and other characteristics of the target. This prediction helps to understand the physical characteristics of the target more accurately and provides key information for subsequent analysis and decision-making.

[0086] Hypersurface geometric parameters refer to parameters that describe the microstructural characteristics of the detection target surface. These parameters include but are not limited to surface roughness, shape factor, size distribution, etc., which together constitute a detailed description of the target surface morphology. In this application scenario, the hypersurface geometric parameters are predicted by structural parameters and are key indicators that match the original lidar data and surface performance mapping information. These parameters are of great significance for in-depth understanding of the physical properties of the detection target, optimizing signal processing algorithms, and improving the accuracy of prediction models.

[0087] In detail, step 160 is an important part of the entire processing flow, and its main purpose is to obtain the hypersurface geometric parameters that match the original laser radar data and surface performance mapping information through structural parameter prediction. In this step, several signal enhancement comparison vectors are first analyzed in depth. These vectors integrate the characteristic information of multiple data sources and provide a rich data basis for structural parameter prediction. By analyzing the change trend and internal laws of these vectors, the microstructural characteristics of the detection target surface can be revealed. Next, the structural parameters of these signal enhancement comparison vectors are predicted using advanced prediction algorithms or models, such as machine learning algorithms or deep learning models. During the prediction process, the various characteristic indicators in the vectors are fully considered, and the original laser radar data and surface performance mapping information are combined to ensure the accuracy and reliability of the prediction results. Finally, through structural parameter prediction, a set of hypersurface geometric parameters that match the original laser radar data and surface performance mapping information can be obtained. These parameters describe the microstructural characteristics of the detection target surface in detail, including key indicators such as surface roughness and shape factor. The acquisition of these parameters not only helps to understand the physical properties of the detection target more deeply, but also provides important data support for subsequent signal processing, model optimization and other work. In general, step 160 successfully transforms the signal enhancement comparison vector into a metasurface geometric parameter with actual physical meaning through the structural parameter prediction technology, adding a new dimension and depth to the entire processing flow.

[0088] The embodiment of the present application significantly improves the detection capability of the LiDAR system through a series of sophisticated data processing processes, especially showing excellent performance in the identification of weak echo signals. This technical solution first deeply mines the feature vectors of the original LiDAR data, the original point cloud detection data, and the surface performance mapping information to fully grasp the multi-dimensional information such as signal status, cloud dynamics, and microstructure. Furthermore, through the innovative inter-class feature focusing knowledge interaction method, information fusion and enhancement between different data sources are achieved, and a signal enhancement comparison vector is generated. Finally, with the help of advanced structural parameter prediction technology, the hypersurface geometric parameters that are highly matched with the original data are determined.

[0089] In this way, not only the design of the isotropic metal disk metasurface is optimized, but also through the integration of the deep learning model, the system can adaptively adjust the metasurface configuration to cope with changing environmental conditions. Therefore, in different scenarios, the embodiments of the present application can ensure that the laser radar system maintains high-sensitivity detection performance. Overall, the embodiments of the present application greatly improve the accuracy and range of target recognition, and provide strong technical support for the application of laser radar technology in multiple fields.

[0090] In some optional embodiments, the feature vector mining is performed on several original lidar data segments corresponding to the original lidar data to obtain the signal-to-noise change trend vector corresponding to each of the original lidar data segments, including: for each of the original lidar data segments, the feature vector mining is performed on the original lidar data segment according to the first knowledge dimension to obtain the first signal quality assessment vector corresponding to the original lidar data segment; the feature vector mining is performed on the original lidar data segment according to the second knowledge dimension to obtain the second signal quality assessment vector corresponding to the original lidar data segment; the knowledge interaction is performed on the first signal quality assessment vector and the second signal quality assessment vector to obtain the signal-to-noise change trend vector corresponding to the original lidar data segment.

[0091] It is understood that in some specific embodiments, the signal enhancement system performs in-depth feature vector mining on the original lidar data to obtain the signal-to-noise change trend vector corresponding to each original lidar data segment. This process is particularly important in the field of meteorology because lidar data plays a key role in meteorological observation, weather forecasting and climate research.

[0092] Specifically, when the signal enhancement system processes a raw lidar data segment, it first mines the data segment according to the first knowledge dimension. The first knowledge dimension here may focus on meteorological factors, such as cloud thickness, precipitation intensity, etc. The system generates a first signal quality assessment vector by analyzing these factors. For example, this vector can contain a set of values, such as [0.8, 0.6, 0.9], which represent the stability of cloud thickness, the uniformity of precipitation intensity, and the intensity of signal reflection. The higher these values ​​are, the more favorable the corresponding meteorological factors are for the transmission and reception of lidar signals.

[0093] Next, the signal enhancement system further mines the data segment based on the second knowledge dimension. The second knowledge dimension may focus more on the dynamic changes of meteorological conditions, such as wind speed, wind direction, and changes in temperature and humidity. The system generates a second signal quality assessment vector by capturing these dynamic features. For example, this vector may contain values ​​similar to [0.7, 0.85, 0.75], corresponding to the stability of wind speed, consistency of wind direction, and suitability of temperature and humidity, respectively. Similarly, the higher the value, the more conducive the dynamic changes in meteorological conditions are to the stable transmission of the signal.

[0094] After obtaining the first signal quality evaluation vector and the second signal quality evaluation vector, the signal enhancement system performs knowledge interaction. The purpose of this step is to merge the information in the two evaluation vectors to obtain a more comprehensive and accurate signal-to-noise change trend vector. For example, through a specific algorithm, the system may obtain a signal-to-noise change trend vector of the form [0.75, 0.7, 0.8]. This vector combines the information of the previous two evaluation vectors and reflects the signal-to-noise ratio change trend of the lidar signal under the current meteorological conditions.

[0095] Through this processing flow, the signal enhancement system can more accurately assess the quality of lidar data and predict possible fluctuations in the signal according to changes in meteorological conditions. This is crucial for meteorological observation stations, weather forecast centers and other institutions, as they rely on accurate meteorological data to make scientific decisions and predictions.

[0096] In this way, the signal enhancement system can generate vectors that reflect the trend of signal-noise changes through multi-level feature vector mining and knowledge interaction, thereby improving the application effect of lidar data in the meteorological field. This not only helps to improve the accuracy of weather forecasts, but also provides more reliable data support for climate research and further promotes the development of meteorological science.

[0097] It is worth mentioning that the first signal quality evaluation vector and the second signal quality evaluation vector are subjected to knowledge interaction to obtain the signal-to-noise change trend vector corresponding to the original laser radar data segment, including:

[0098] First, an interaction model is constructed, which is capable of receiving and processing the first signal quality evaluation vector and the second signal quality evaluation vector. The interaction model adopts a deep learning network structure, including but not limited to a convolutional neural network, a recurrent neural network or a self-attention mechanism network, which is trained to capture the complex relationship between the two evaluation vectors;

[0099] Next, the first signal quality evaluation vector and the second signal quality evaluation vector are used as dual inputs and fed into two parallel processing branches of the interaction model. Each branch contains multiple hidden layers for extracting deep features of their respective evaluation vectors. These hidden layers increase the expressiveness of the model through nonlinear activation functions (such as ReLU, Sigmoid, or Tanh), enabling it to capture complex patterns in the data.

[0100] Then, in the middle layer of the model, an interaction module is introduced, which is responsible for fusing the features extracted by the two branches. This interaction module can be implemented in a variety of ways, such as feature concatenation, dot product attention mechanism, or gated fusion, to ensure that the information of the two evaluation vectors can fully interact and generate a joint feature representation that integrates the knowledge of both parties;

[0101] Finally, the joint feature representation is mapped to the signal-noise change trend vector through an output layer. This output layer can be a fully connected layer, followed by an appropriate activation function (such as Softmax or Sigmoid) to ensure that the output signal-noise change trend vector is within a reasonable numerical range and can accurately reflect the signal quality change trend of the original lidar data segment.

[0102] In addition, to improve the generalization ability and performance of the model, regularization techniques (such as L1 regularization, L2 regularization, or Dropout) can be used to prevent overfitting, and appropriate optimization algorithms (such as Adam, RMSprop, or SGD) can be used to train the model to achieve the best performance.

[0103] Through the above technical solution, it is possible to achieve effective knowledge interaction between the first signal quality assessment vector and the second signal quality assessment vector, thereby accurately obtaining the signal-to-noise change trend vector corresponding to the original lidar data segment.

[0104] In some other possible embodiments, the step of obtaining the several original lidar data segments includes: disassembling the original lidar data based on the data scanning kernel to obtain the several original lidar data segments; each of the original lidar data segments includes key field indexes of several associated original lidar data segments.

[0105] Based on this embodiment, when processing the raw laser radar data, the signal enhancement system adopts a disassembly method based on the data scanning core to obtain a number of raw laser radar data segments. This step is particularly important in the field of meteorology because it can help to more carefully analyze the meteorological conditions in different regions and different time periods.

[0106] Specifically, the signal enhancement system first determines a suitable data scanning core, which can be regarded as a "window" for data decomposition. Through this scanning core, the system slides on the original lidar data according to the set step size or rule, thereby decomposing the data into several smaller data segments, namely the original lidar data segments.

[0107] Each raw LiDAR data segment includes not only specific meteorological data, such as cloud distribution, precipitation conditions, etc., but also several associated key field indexes. These key field indexes are similar to data tags or metadata, which provide important information about the data segment, such as data collection time, geographic location, scanning angle, etc.

[0108] For example, there is a piece of raw lidar data that records the weather conditions in a certain area within a day. By setting a suitable data scanning core, the signal enhancement system can break this data into multiple hourly data segments. Each data segment will be accompanied by a set of key field indexes, such as "2023-04-25, 08:00:00 to 09:00:00", "Longitude 116.4°, Latitude 39.9°", etc. These indexes can help accurately understand the specific background and context of each data segment.

[0109] In actual operation, these key field indexes can exist in the form of numerical feature vectors. For example, a key field index vector can be [2023, 4, 25, 8, 0, 0, 116.4, 39.9], where the first six digits represent the start time of data collection (year, month, day, hour, minute, second), and the last two digits represent the longitude and latitude of the geographic location. Such numerical feature vectors are convenient for computers to process and analyze efficiently.

[0110] In this way, the signal enhancement system can process and analyze the original lidar data more flexibly, thereby providing more accurate and detailed meteorological information. This not only helps to improve the accuracy of weather forecasts, but also provides more valuable data support for climate research, environmental monitoring and other fields. In this way, by disassembling the original lidar data based on the data scanning core and obtaining the original lidar data segments containing key field indexes, the signal enhancement system can process and analyze meteorological data more effectively and improve the accuracy and practicality of meteorological information. This technical solution brings new possibilities for data processing and analysis in the meteorological field and has significant practical application value.

[0111] In other optional embodiments, the feature vector mining is performed on several hypertable structure model data corresponding to the surface performance mapping information to obtain the quantitative structure geometric distribution vector corresponding to each group of the hypertable structure model data, including: for each group of the hypertable structure model data, the spatial arrangement state of the hypertable structure model data is identified to obtain the target spatial arrangement state information set corresponding to the hypertable structure model data; the feature vector mining is performed on the target spatial arrangement state information set to obtain the quantitative structure geometric distribution vector corresponding to the hypertable structure model data.

[0112] Based on this embodiment, the signal enhancement system will perform in-depth feature vector mining on several hypertable structure model data corresponding to the surface performance mapping information to obtain the quantitative structure geometric distribution vector corresponding to each set of hypertable structure model data. This process is particularly important in meteorological applications because it can help more accurately understand and predict the impact of meteorological conditions on the surface structure.

[0113] Specifically, when the signal enhancement system processes each set of hypertable structure model data, it first performs spatial arrangement state recognition. The purpose of this step is to analyze the distribution and arrangement of the hypertable structure model data in space, so as to obtain the corresponding target spatial arrangement state information set. For example, a hypertable structure model data may represent a specific area of ​​a surface, which contains spatial distribution information of multiple elements such as terrain, vegetation, and water bodies. Through spatial arrangement state recognition, the system can extract the relative positions and relationships between these elements to form a comprehensive description of the spatial arrangement state.

[0114] Next, the signal enhancement system performs feature vector mining on the target spatial arrangement state information set. This step uses mathematical and statistical methods to convert the complex information in the spatial arrangement state information set into a concise and quantifiable feature vector form. These feature vectors can capture the core geometric features and spatial distribution patterns of the hypertable structure model data.

[0115] For a more intuitive understanding, let's take a specific example. There is a set of hypertable structure model data representing the surface structure of a mountainous area. Through spatial arrangement state recognition, the system may identify the location and shape of key landform features such as peaks, valleys, and rivers. Then, in the feature vector mining stage, the system can generate a quantitative structural geometric distribution vector, such as [0.8, 0.6, 0.9, 0.7], where each value represents the distribution density of the corresponding landform feature in space, shape complexity and other quantitative indicators.

[0116] Through such a processing flow, the signal enhancement system can generate a set of accurate quantitative structural geometric distribution vectors, which not only reflect the core geometric features of the hypertable structure model data, but also facilitate subsequent data analysis and model training. In the field of meteorology, such information is of great significance for predicting the impact of surface structure on meteorological conditions and optimizing meteorological models. In this way, the signal enhancement system can obtain accurate quantitative structural geometric distribution vectors by identifying the spatial arrangement state and mining the feature vectors of the hypertable structure model data. These vectors not only enrich the understanding of the surface structure, but also provide strong data support for meteorological forecasting and model optimization, further improving the accuracy and practicality of meteorological services.

[0117] In some other preferred technical schemes, the feature vector mining of the target spatial arrangement state information set to obtain the quantized structural geometric distribution vector corresponding to the hypertable structure model data includes: performing knowledge mapping on the target spatial arrangement state information set to obtain a number of first spatial arrangement state knowledge corresponding to the target spatial arrangement state information set; performing interval numerical mapping on the several first spatial arrangement state knowledge to obtain the second spatial arrangement state knowledge corresponding to each of the first spatial arrangement state knowledge; performing feature collision on a number of the second spatial arrangement state knowledge to obtain the third spatial arrangement state knowledge corresponding to each of the second spatial arrangement state knowledge; performing linear quantization on a number of the third spatial arrangement state knowledge to obtain the quantized structural geometric distribution vector.

[0118] In this technical solution, the signal enhancement system conducts detailed feature vector mining on the target spatial arrangement state information set to obtain the quantitative structural geometric distribution vector corresponding to the hypertable structure model data. This process can assist in a deeper understanding of the interaction between surface structure and meteorological conditions in meteorological applications.

[0119] First, the signal enhancement system performs knowledge mapping on the target spatial arrangement state information set. This process aims to transform the original spatial arrangement state information into more abstract and representative first spatial arrangement state knowledge. For example, a specific spatial arrangement state information may be "the alternating distribution of mountains and plains in a certain area". Through knowledge mapping, the system can abstract it into the first spatial arrangement state knowledge of "terrain diversity".

[0120] Next, the system performs interval numerical mapping on these first spatial arrangement state knowledge. This means converting abstract knowledge into specific numerical representations to facilitate subsequent numerical calculations and analysis. For example, the knowledge of "terrain diversity" can be mapped to a specific numerical interval, such as [0, 1], where 0 represents a single terrain and 1 represents extremely diverse terrain.

[0121] Then, the signal enhancement system performs feature collision on several second spatial arrangement state knowledge. Feature collision is a method of generating new features by comparing and fusing different features. In this process, the system analyzes the associations and differences between different second spatial arrangement state knowledge to generate more comprehensive and comprehensive third spatial arrangement state knowledge. For example, by colliding the two second spatial arrangement state knowledge of "terrain diversity" and "vegetation coverage", the system may generate a new third spatial arrangement state knowledge, namely "the combined influence of terrain and vegetation".

[0122] Finally, the system linearly quantizes several third-space arrangement state knowledge to obtain the quantized structural geometric distribution vector. Linear quantization is to convert nonlinear or complex knowledge structures into linear numerical representations to facilitate mathematical operations and comparative analysis. For example, the third-space arrangement state knowledge of "combined impact of terrain and vegetation" can be quantified into a specific numerical vector, such as [0.6, 0.8, 0.5], where the numerical values ​​represent the degree of influence of different aspects.

[0123] For example, there is a set of hypertable structure model data that represents the surface structure of a certain area. Through the above process, the signal enhancement system may generate a quantitative structure geometric distribution vector, such as [0.4, 0.7, 0.3]. This vector not only reflects the spatial arrangement characteristics of the surface structure of the area, but also facilitates comparison and analysis with data from other regions or different time points.

[0124] In summary, through this series of sophisticated processing procedures, the signal enhancement system can generate accurate quantitative structural geometric distribution vectors, thereby revealing the relationship between surface structure and meteorological conditions in more depth. This not only helps to improve the accuracy of meteorological forecasts, but also provides strong data support for environmental protection, resource planning and other fields. Therefore, this technical solution has broad application prospects and significant practical value in the field of meteorology.

[0125] In some other possible embodiments, for each group of the quantization structure geometric distribution vectors, the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, several signal-noise change trend vectors and the quantization structure geometric distribution vector are subjected to knowledge interaction based on inter-class feature focusing to obtain a signal enhancement comparison vector, including: performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, and several signal-noise change trend vectors to obtain a first inter-class signal focus linkage vector; for each group of the quantization structure geometric distribution vectors, performing knowledge interaction on the first inter-class signal focus linkage vector and the quantization structure geometric distribution vector to obtain the signal enhancement comparison vector.

[0126] Based on this embodiment, the signal enhancement system performs a series of complex operations to obtain a signal enhancement comparison vector. This process is particularly important in the field of meteorology because it can improve the ability to analyze meteorological signals, thereby more accurately predicting and evaluating weather conditions.

[0127] First, the signal enhancement system performs knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, and several signal-noise change trend vectors. The purpose of this step is to extract the common features and correlation information between these vectors to form the first inter-class signal focusing linkage vector.

[0128] Specifically, the original signal state monitoring vector can contain the original meteorological signal data received by the weather radar or satellite, the laser point cloud spatiotemporal linkage vector provides information about the three-dimensional spatial distribution and temporal changes of the cloud layer, and the signal-to-noise change trend vector reflects the change in the noise level in the signal. Through the knowledge interaction of inter-class feature focus, the system can identify the similarities and differences between these vectors, and then generate the first inter-class signal focus linkage vector.

[0129] For example, the original signal state monitoring vector is [1.2, 0.8, 1.0], the laser point cloud spatiotemporal linkage vector is [0.9, 1.1, 1.0], and the signal-to-noise change trend vector is [0.1, 0.2, 0.15]. Through knowledge interaction, the system finds that these vectors have high values ​​in the third element, thus generating the first inter-class signal focus linkage vector, such as [0.8, 0.9, 1.2], where the high value of the third element reflects the common characteristics of these original vectors at this point.

[0130] Next, the signal enhancement system performs knowledge interaction between the first inter-class signal focusing linkage vector and these vectors for each set of quantized structural geometric distribution vectors. The quantized structural geometric distribution vectors describe the geometric structure and spatial distribution characteristics of the surface or cloud layer, which are closely related to the state and change trend of meteorological signals.

[0131] Through the knowledge interaction with the first-class inter-signal focus linkage vector, the system can further extract the signal features related to the surface or cloud structure, thereby generating a signal enhancement comparison vector. This vector not only contains the information of the original meteorological signal, but also integrates the features related to the surface or cloud structure, making the analysis of meteorological conditions more accurate and comprehensive.

[0132] For example, a set of quantized structure geometry distribution vectors is [0.7, 0.6, 0.8], and after knowledge interaction with the first inter-class signal focus linkage vector [0.8, 0.9, 1.2], a signal enhancement comparison vector such as [0.9, 0.8, 1.3] may be generated. The higher value of the third element of this vector may reflect the enhanced effect of meteorological signals when the cloud layer is thick or the surface structure is complex in the area.

[0133] In summary, through the knowledge interaction operation based on inter-class feature focusing, the signal enhancement system can generate a signal enhancement comparison vector that integrates multiple information. This not only improves the accuracy of meteorological signal analysis, but also provides more accurate and comprehensive data support for subsequent meteorological forecasting and evaluation. Therefore, this technical solution has significant application value and practical significance in the field of meteorology.

[0134] It is worth mentioning that the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, and a plurality of signal-to-noise change trend vectors are subjected to knowledge interaction based on inter-class feature focusing to obtain a first inter-class signal focusing linkage vector, including:

[0135] Feature extraction step: extract key eigenvalues ​​from the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, and the signal-noise change trend vector, respectively. These eigenvalues ​​include but are not limited to signal strength, frequency distribution, noise level, and change trend, etc.;

[0136] Feature mapping step: construct a feature mapping model that can map the feature values ​​extracted from different vectors into a unified feature space to facilitate comparison and fusion of inter-class features;

[0137] Inter-class feature focusing step: In the unified feature space, by calculating the similarity or correlation between different vector features, the features with common or complementary information are identified to form a focused feature set;

[0138] Linkage vector generation steps: Based on the focused feature set, weighted average, feature fusion or other complex mathematical transformation methods are used to generate the first inter-class signal focused linkage vector, which integrates the key information from different original vectors and can more comprehensively and accurately reflect the signal status and its changing trend.

[0139] Further, for each group of the quantization structure geometric distribution vectors, knowledge interaction is performed on the first inter-class signal focus linkage vector and the quantization structure geometric distribution vector to obtain the signal enhancement comparison vector, including:

[0140] Structural feature extraction step: extract key structural features from the quantized structural geometric distribution vector, such as the undulation of the terrain, the thickness and distribution of the cloud layer, etc.;

[0141] Signal and structural feature correlation step: by building a correlation model, analyzing the potential connection between the first inter-class signal focus linkage vector and the extracted structural features, and identifying the correlation between the signal state and the surface or cloud structure;

[0142] Knowledge interaction step: Based on the identified correlation, the first inter-class signal focusing linkage vector is modified or enhanced to more accurately reflect the signal state under the influence of the surface or cloud structure;

[0143] Comparison vector generation step: Compare the first inter-class signal focusing linkage vector after knowledge interaction with the original quantized structure geometric distribution vector to generate a signal enhancement comparison vector, which not only contains the state information of the signal, but also incorporates the interaction with the surface or cloud structure, thereby improving the signal analysis accuracy and prediction ability.

[0144] In detail, in the meteorological field, the signal enhancement system generates a signal enhancement comparison vector through a series of complex operations, thereby improving the accuracy and prediction ability of the meteorological signal. The following is a detailed example of the process.

[0145] First, the signal enhancement system performs the feature extraction step. It extracts key meteorological signal features, such as signal strength, frequency distribution, etc., from the original signal state monitoring vector. For example, the original signal state monitoring vector may contain real-time data on temperature, air pressure, and humidity in a certain area, from which the system extracts the characteristic values ​​of these data. At the same time, the system also extracts the spatiotemporal variation characteristics of the cloud layer, such as cloud height, moving speed, and density, from the laser point cloud spatiotemporal linkage vector, and extracts the noise level and its variation trend from the signal-to-noise variation trend vector.

[0146] Next is the feature mapping step. The signal enhancement system builds a feature mapping model that is able to map the feature values ​​extracted from different vectors into a unified feature space. This is done to facilitate the comparison and fusion of different types of features. In this unified feature space, various feature values ​​are represented in the same way, making it easier to identify similarities or correlations between them.

[0147] In the inter-class feature focusing step, the signal enhancement system identifies features with common or complementary information by calculating the similarity or correlation between different vector features in the unified feature space. These features are combined into a focused feature set, which can more comprehensively reflect the state of the meteorological signal and its changing trend.

[0148] The next step is to generate the linkage vector. Based on the focused feature set, the signal enhancement system uses weighted averaging, feature fusion or other complex mathematical transformation methods to generate the first inter-class signal focused linkage vector. This vector integrates key information from different original vectors, so it can more comprehensively and accurately reflect the state of the meteorological signal and its changing trend.

[0149] Furthermore, when processing each set of quantized structural geometric distribution vectors, the signal enhancement system first performs a structural feature extraction step. It extracts key structural features from the quantized structural geometric distribution vectors, such as the undulation of the terrain, the thickness and distribution of the clouds, etc. These structural features are crucial for understanding the state of the meteorological signal under the influence of the surface or cloud structure.

[0150] Next is the step of associating the signal with the structural features. The signal enhancement system analyzes the potential connection between the first-class inter-signal focus linkage vector and the extracted structural features by building a correlation model. The purpose of this is to identify the correlation between the signal state and the surface or cloud structure, so as to have a deeper understanding of the changing laws of meteorological signals.

[0151] In the knowledge interaction step, the signal enhancement system modifies or enhances the first inter-class signal focus linkage vector based on the identified correlation. This allows the vector to more accurately reflect the state of the meteorological signal under the influence of the surface or cloud structure. For example, if the system finds that the temperature in a certain area is closely related to the terrain, it can adjust the temperature data accordingly based on the terrain characteristics.

[0152] The last step is to generate the comparison vector. The signal enhancement system compares the first inter-class signal focus linkage vector after knowledge interaction with the original quantized structure geometric distribution vector to generate a signal enhancement comparison vector. This vector not only contains the state information of the meteorological signal, but also incorporates the interaction with the surface or cloud structure. Therefore, it can more accurately reflect the actual meteorological conditions and improve the signal analysis accuracy and prediction ability.

[0153] It can be seen that the signal enhancement system generates signal enhancement comparison vectors through a series of complex operations, which fully consider the various influencing factors of meteorological signals, including the original signal state, the spatiotemporal linkage of laser point clouds, the trend of signal-to-noise changes, and the surface and cloud structures. In this way, the system can generate more comprehensive and accurate meteorological signal data, providing more reliable support for weather forecasting and climate research.

[0154] In some further optional embodiments, for each group of the quantized structure geometric distribution vectors, the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, several of the signal-to-noise change trend vectors and the quantized structure geometric distribution vector are subjected to knowledge interaction based on inter-class feature focusing to obtain a signal enhancement comparison vector, including: performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector and several of the signal-to-noise change trend vectors to obtain a first inter-class signal focus linkage vector; for each group of the quantized structure geometric distribution vectors, performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector and the quantized structure geometric distribution vector to obtain a second inter-class signal focus linkage vector; performing knowledge interaction on the first inter-class signal focus linkage vector and the second inter-class signal focus linkage vector to obtain the signal enhancement comparison vector.

[0155] In this embodiment, the signal enhancement system performs a series of complex operations to obtain the signal enhancement comparison vector. These operations are particularly important in meteorological applications because they help improve the accuracy and reliability of meteorological signals, thereby improving the accuracy of weather forecasts and climate research.

[0156] First, the signal enhancement system performs knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, and several signal-noise change trend vectors. The purpose of this step is to extract common features from different types of signal vectors and generate the first inter-class signal focus linkage vector. For example, the original signal state monitoring vector is [1.5, 0.7, 1.2], which represents the monitoring data of temperature, humidity and wind speed in a certain area; the laser point cloud spatiotemporal linkage vector is [0.8, 1.3, 1.1], which reflects the height, density and movement speed of the cloud layer; the signal-noise change trend vector is [0.2, 0.3, 0.25], which represents the change of noise in the signal. Through knowledge interaction, the system finds that these vectors have common change trends in certain features, thereby generating the first inter-class signal focus linkage vector, such as [1.2, 1.0, 1.1], which integrates the key features of the original signal.

[0157] Next, for each group of quantized structure geometric distribution vectors, the signal enhancement system performs knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector and the quantized structure geometric distribution vector. The purpose of this step is to explore the relationship between the geometric structure of the surface or cloud layer and the meteorological signal, and generate a second inter-class signal focusing linkage vector. For example, the quantized structure geometric distribution vector of a certain group is [0.6, 0.8, 0.7], which represents the terrain undulation, surface cover type and cloud structure of the area. Through knowledge interaction with the original signal state monitoring vector, the system finds that the terrain undulation affects the temperature, the surface cover type affects the humidity, and the cloud structure is related to the wind speed. Therefore, the generated second inter-class signal focusing linkage vector may be [1.3, 0.9, 1.0], which reflects the specific impact of the surface and cloud structure on the meteorological signal.

[0158] Finally, the signal enhancement system performs knowledge interaction on the first inter-class signal focus linkage vector and the second inter-class signal focus linkage vector. The purpose of this step is to combine the characteristics of different types of signals with the influence of the surface and cloud structure to generate the final signal enhancement comparison vector. Taking the two previously generated inter-class signal focus linkage vectors as an example, [1.2, 1.0, 1.1] and [1.3, 0.9, 1.0], through knowledge interaction, the system finds that certain features are significantly expressed in both vectors, thereby generating a signal enhancement comparison vector such as [1.4, 1.1, 1.2]. This vector not only contains the characteristics of the original meteorological signal, but also takes into account the influence of the surface and cloud structure on the signal, so it can more accurately reflect the actual meteorological conditions.

[0159] In this way, the signal enhancement system can generate a signal enhancement comparison vector that integrates multiple information and influencing factors. This not only improves the accuracy and reliability of meteorological signals, but also provides a more accurate data basis for weather forecasting and climate research.

[0160] In some further optional embodiments, the knowledge interaction based on inter-class feature focusing is performed on the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, and several of the signal-noise change trend vectors to obtain a first inter-class signal focus linkage vector, including: performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector and the laser point cloud spatiotemporal linkage vector to obtain a third inter-class signal focus linkage vector; performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector and several of the signal-noise change trend vectors to obtain a fourth inter-class signal focus linkage vector; performing knowledge interaction on the third inter-class signal focus linkage vector and the fourth inter-class signal focus linkage vector to obtain the first inter-class signal focus linkage vector; the knowledge size of the first inter-class signal focus linkage vector, the knowledge size of the third inter-class signal focus linkage vector, and the knowledge size of the fourth inter-class signal focus linkage vector are the same.

[0161] In this embodiment, the signal enhancement system performs knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, and the signal-to-noise change trend vector to obtain the first inter-class signal focusing linkage vector. This process involves multiple steps and ensures that the knowledge size of the inter-class signal focusing linkage vector is the same, which facilitates subsequent data processing and analysis.

[0162] First, the signal enhancement system performs knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector and the laser point cloud spatiotemporal linkage vector. The purpose of this step is to explore the potential connection between meteorological signals and the spatiotemporal changes of clouds. For example, the original signal state monitoring vector can contain meteorological parameters such as temperature, humidity, and wind speed, while the laser point cloud spatiotemporal linkage vector reflects the distribution, movement, and changes of clouds. Through knowledge interaction, the system can identify the correlation between the two, such as the impact of cloud movement on wind speed, thereby generating a third inter-class signal focusing linkage vector.

[0163] Next, the signal enhancement system performs knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector and several signal-noise change trend vectors. This step aims to explore the relationship between meteorological signals and noise change trends. The signal-noise change trend vector reflects the level and change trend of noise in the signal, which is crucial for evaluating the accuracy and reliability of meteorological signals. Through knowledge interaction with the original signal state monitoring vector, the system can identify the impact of noise on meteorological signals and generate the fourth inter-class signal focus linkage vector accordingly.

[0164] Then, the signal enhancement system performs knowledge interaction on the third-class inter-signal focus linkage vector and the fourth-class inter-signal focus linkage vector. The purpose of this step is to fuse the correlations mined in the first two steps to generate a more comprehensive and accurate first-class inter-signal focus linkage vector. By comprehensively considering the impact of cloud spatiotemporal changes and noise change trends on meteorological signals, the system can generate a vector that integrates multiple aspects of information, which can more comprehensively reflect the actual state of meteorological signals.

[0165] It is worth noting that the knowledge size of the first inter-class signal focusing linkage vector, the knowledge size of the third inter-class signal focusing linkage vector, and the knowledge size of the fourth inter-class signal focusing linkage vector are all the same. This means that these vectors are consistent in data structure and dimension, which facilitates subsequent data processing, comparison, and analysis. This design not only improves the efficiency of data processing, but also ensures the comparability between the inter-class signal focusing linkage vectors.

[0166] It can be seen that the signal enhancement system successfully merges the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector and the signal-noise change trend vector into the first type of inter-signal focus linkage vector through a series of complex knowledge interaction operations. In this process, the system not only explores the potential connection between meteorological signals and the spatiotemporal changes of clouds and noise change trends, but also ensures that the knowledge size of the inter-signal focus linkage vectors is the same, which facilitates subsequent data processing and analysis. These operations jointly improve the accuracy and reliability of meteorological signals and provide a more accurate data basis for weather forecasting and climate research.

[0167] In other preferred embodiments, the knowledge interaction between the first inter-class signal focusing linkage vector and the quantization structure geometric distribution vector to obtain the signal enhancement comparison vector includes: performing knowledge interaction based on inter-class feature focusing on the first inter-class signal focusing linkage vector and the quantization structure geometric distribution vector to obtain a target signal quality deduction vector; performing knowledge interaction between the first inter-class signal focusing linkage vector and the target signal quality deduction vector to obtain the signal enhancement comparison vector.

[0168] Based on this embodiment, the signal enhancement system adopts a more refined method to process the first inter-class signal focusing linkage vector and the quantized structure geometric distribution vector to obtain the signal enhancement comparison vector. This process involves two knowledge interactions based on inter-class feature focusing, aiming to further improve the signal analysis accuracy and prediction accuracy.

[0169] First, the signal enhancement system performs knowledge interaction based on inter-class feature focusing on the first inter-class signal focus linkage vector and the quantized structure geometry distribution vector. The quantized structure geometry distribution vector describes the geometric features of the surface or atmospheric structure, such as terrain height, cloud thickness, etc. The first inter-class signal focus linkage vector has integrated information such as the original signal state, the spatiotemporal changes of the laser point cloud, and the signal-to-noise change trend. In this step of knowledge interaction, the system aims to identify the deep connection between the signal state and the surface or atmospheric structure.

[0170] For example, the system finds that under certain terrain or cloud structures, the signal strength will show a specific change trend. By mining these potential associations, the system can generate a target signal quality deduction vector. This vector not only reflects the state of the signal in the current environment, but also predicts the possible change trend and quality of the signal in the future.

[0171] Next, the signal enhancement system performs knowledge interaction between the first inter-class signal focus linkage vector and the target signal quality deduction vector. The purpose of this step is to combine the deduced signal quality changes with the original focus linkage vector to generate a more accurate signal enhancement comparison vector. In this process, the system can adjust the original focus linkage vector based on the prediction results of the deduction vector to reflect possible changes in the future signal state.

[0172] This two-step knowledge interaction method enables the signal enhancement system to more accurately capture the complex relationship between the signal state and the surface or atmospheric structure, and optimize the processing and analysis of the signal based on these relationships. In this way, the system can not only improve the real-time analysis accuracy of the signal, but also enhance the ability to predict future signal states.

[0173] In summary, through the refined processing methods in these preferred embodiments, the signal enhancement system can more effectively integrate and utilize information from multiple data sources to improve the accuracy and reliability of meteorological signals. This not only helps to improve the accuracy of weather forecasts, but also provides more powerful data support for climate research, disaster warning and other fields.

[0174] In some optional embodiments, the structural parameter prediction of several signal enhancement comparison vectors is performed to obtain the hypersurface geometric parameters that match both the original lidar data and the surface performance mapping information, including: signal stream integration of several signal enhancement comparison vectors to obtain the global inter-class signal focusing linkage vector corresponding to each group of signal enhancement comparison vectors; structural parameter prediction of several global inter-class signal focusing linkage vectors to obtain the hypersurface geometric parameters.

[0175] In this embodiment, the signal enhancement system performs a series of complex operations to obtain the hypersurface geometry parameters that match the original lidar data and the surface performance mapping information. This process involves two key steps: signal flow integration and structural parameter prediction, which aims to improve the accuracy and application effectiveness of meteorological data.

[0176] First, the signal enhancement system performs signal stream integration on several signal enhancement comparison vectors. Signal stream integration is a data processing process that aims to fuse the information in multiple signal enhancement comparison vectors into a global data representation. Through this step, the system can extract the key features in each set of signal enhancement comparison vectors, and then generate a global inter-class signal focus linkage vector. This global vector not only contains various feature information of the original signal, but also reflects the correlation and change trend between different signals.

[0177] For example, there are multiple signal enhancement comparison vectors corresponding to different time periods or meteorological conditions. Through signal stream integration, the useful information in these vectors can be gathered together to form a more comprehensive and rich data representation. In this way, the global characteristics and dynamic changes of meteorological signals can be captured more accurately.

[0178] Next, the signal enhancement system predicts the structural parameters of several global inter-class signal focusing linkage vectors. Structural parameter prediction is a process based on data analysis and machine learning algorithms, which aims to derive hypersurface geometric parameters from global inter-class signal focusing linkage vectors. Hypersurface geometric parameters are advanced parameters that describe the structural characteristics of the surface or atmosphere, and are of great significance in fields such as meteorological forecasting and environmental monitoring.

[0179] In the process of structural parameter prediction, the system can use advanced machine learning models, such as deep learning networks, to analyze and predict the global inter-class signal focus linkage vector. Through these models, the system can learn the complex patterns and underlying laws in the data and derive accurate metasurface geometric parameters based on them.

[0180] Finally, through the combination of these two key steps, the signal enhancement system successfully obtained the metasurface geometric parameters that matched both the original lidar data and the surface performance mapping information. This means that these parameters not only reflect the actual surface or atmospheric structure observed by the lidar, but are also highly consistent with the surface performance mapping information obtained by other means.

[0181] In this way, the signal enhancement system realizes in-depth analysis and accurate prediction of meteorological signals through the methods in these embodiments. This not only improves the accuracy and reliability of meteorological data, but also provides strong support for research and application in related fields. For example, in weather forecasting, accurate hypersurface geometric parameters can more accurately assist in predicting the occurrence and development trends of weather phenomena such as wind, rain, snow and fog; in environmental monitoring, these parameters can be used to evaluate changes in environmental indicators such as air quality and hydrological conditions.

[0182] It is worth mentioning that the structural parameters of several global inter-class signal focusing linkage vectors are predicted to obtain the hypersurface geometric parameters, including: constructing a multi-dimensional deep learning model that integrates convolutional neural networks and long short-term memory networks; inputting several global inter-class signal focusing linkage vectors as input data into the deep learning model; through the multi-level feature extraction and timing dependency analysis of the deep learning model, the global inter-class signal focusing linkage vectors are deeply mined to capture the potential rules and complex associations therein; using the output layer of the deep learning model to map and transform the extracted features to generate a parameter representation corresponding to the hypersurface geometric structure; iteratively optimizing the generated parameters through an optimization algorithm until the preset accuracy requirements are met, and finally obtaining the hypersurface geometric parameters.

[0183] In this way, by building a multi-dimensional deep learning model and integrating the advantages of convolutional neural networks and long short-term memory networks, we can comprehensively and deeply mine the information in the global inter-class signal focus linkage vector. Through the powerful feature extraction and time series analysis capabilities of the deep learning model, we can capture the complex associations and potential laws between vectors, and then generate accurate hypersurface geometric parameters. This not only improves the accuracy and efficiency of parameter prediction, but also provides more reliable data support for subsequent meteorological analysis, prediction and decision-making.

[0184] In detail, in the process of predicting the structural parameters of several global inter-class signal focusing linkage vectors to obtain the geometric parameters of the hypersurface, the signal enhancement system adopts an advanced and complex technical solution. The core of this solution is to build a multi-dimensional deep learning model, which cleverly combines the advantages of convolutional neural networks (CNNs) and long short-term memory networks (LSTMs). First, the signal enhancement system feeds several global inter-class signal focusing linkage vectors as input data to this deep learning model. These global vectors contain rich meteorological signal characteristics and temporal change information, which is the basis for the model to conduct deep mining. Then, the deep learning model will exert its powerful multi-level feature extraction capabilities. The convolutional neural network part is responsible for extracting spatial structural features from the global vectors, such as the distribution pattern and intensity change of the signal. The long short-term memory network focuses on capturing the temporal dependence and change trend of these features. Through the joint action of these two networks, the model can more comprehensively understand the inherent laws and complex associations of the global inter-class signal focusing linkage vectors. Subsequently, the output layer of the deep learning model maps and transforms the extracted features. The purpose of this step is to convert these features into parameter representations corresponding to the geometric structure of the hypersurface. In this way, the model can convert complex meteorological signal data into geometric parameters with actual physical meaning, which facilitates subsequent meteorological analysis. Finally, the signal enhancement system uses an optimization algorithm to iteratively optimize the generated parameters. This process continues until the generated parameters meet the preset accuracy requirements. In this way, the system can ensure that the final obtained hypersurface geometric parameters are highly accurate and reliable. In summary, by constructing a multi-dimensional deep learning model and integrating the advantages of convolutional neural networks and long short-term memory networks, the signal enhancement system can comprehensively and deeply mine the information in the global inter-class signal focusing linkage vector. This technical solution not only significantly improves the accuracy and efficiency of parameter prediction, but also provides more reliable data support for subsequent meteorological analysis, prediction and decision-making. This means that when dealing with complex and changeable meteorological conditions, the geometric characteristics of the surface or atmospheric structure can be more accurately grasped, so as to make more scientific and reasonable decisions.

[0185] In some possible steps, the signal stream integration is performed on several signal enhancement comparison vectors to obtain a global inter-class signal focusing linkage vector corresponding to each group of the signal enhancement comparison vectors, including: clustering the several signal enhancement comparison vectors to obtain several signal enhancement comparison vectors under several classification clusters; for several signal enhancement comparison vectors under each classification cluster, the signal stream integration is performed on the several signal enhancement comparison vectors under the classification cluster to obtain a global inter-class signal focusing linkage vector corresponding to each group of the signal enhancement comparison vectors under the classification cluster; knowledge interaction is performed on the several global inter-class signal focusing linkage vectors under the several classification clusters to obtain a global inter-class signal focusing linkage vector corresponding to each group of the signal enhancement comparison vectors.

[0186] In this embodiment, the signal enhancement system adopts a meticulous signal flow integration method to obtain the global inter-class signal focus linkage vector corresponding to each set of signal enhancement comparison vectors. This process involves clustering processing, signal flow integration within classification clusters, and knowledge interaction between classification clusters, aiming to improve the precision and accuracy of signal processing.

[0187] First, the signal enhancement system performs clustering on several signal enhancement comparison vectors. Clustering is a data analysis technique used to group similar data points into the same cluster. Here, the system divides the signal enhancement comparison vectors into several classification clusters based on their characteristics, such as signal strength, change trend, etc. Each classification cluster contains a group of signal enhancement comparison vectors with similar characteristics.

[0188] For example, if one set of signal enhancement comparison vectors reflects the signal status in clear weather, and another set reflects the signal status in rainy weather, clustering processing can classify these vectors into different classification clusters.

[0189] Next, the signal enhancement system performs signal stream integration for several signal enhancement comparison vectors under each classification cluster. In this step, the system conducts a comprehensive analysis of the signal enhancement comparison vectors within each classification cluster to extract the commonalities and characteristics between them. Through signal stream integration, the system can generate a global inter-class signal focus linkage vector that represents the characteristics of the classification cluster. This global vector integrates the key information of all vectors within the classification cluster and reflects the overall status and trend of the signal under the classification cluster.

[0190] Continuing with the above example, for the classification cluster reflecting clear weather, through signal stream integration, the system can generate a global inter-class signal focus linkage vector, which represents the overall characteristics and changing trends of the signal under clear weather.

[0191] Finally, the signal enhancement system performs knowledge interaction on the global inter-class signal focus linkage vectors under several classification clusters. Knowledge interaction is an information fusion process that aims to cross-validate and complement the global vectors under different classification clusters to obtain a more comprehensive and accurate global inter-class signal focus linkage vector. Through this step, the system can comprehensively consider the signal status under different meteorological conditions and further improve the representativeness and reliability of the global vector.

[0192] In this way, the signal enhancement system realizes the fine processing and analysis of the signal enhancement comparison vector. This processing method not only takes into account the local characteristics of the signal, but also integrates the global information, thereby improving the accuracy and robustness of signal processing. The global inter-class signal focusing linkage vector finally obtained can more comprehensively reflect the state and change trend of the meteorological signal, providing strong data support for subsequent meteorological analysis and prediction.

[0193] In some independent embodiments, knowledge interaction is performed on several global inter-class signal focus linkage vectors under several classification clusters to obtain global inter-class signal focus linkage vectors corresponding to each group of signal enhancement comparison vectors, including: constructing an interactive knowledge fusion platform, which supports multimodal data interaction and dynamic knowledge graph construction; loading the global inter-class signal focus linkage vectors under several classification clusters into the interactive knowledge fusion platform to form initialized knowledge nodes; using the platform's interactive mechanism to perform dynamic association analysis on each knowledge node, identify and establish a similarity network between nodes; based on the similarity network, information interaction and fusion of global inter-class signal focus linkage vectors across classification clusters are performed, so that knowledge under different classification clusters can be mutually referenced and enhanced; through the platform's dynamic optimization algorithm, the global inter-class signal focus linkage vectors after interaction are adaptively adjusted and improved to ensure the accuracy and consistency of the information; finally, the global inter-class signal focus linkage vectors corresponding to each group of signal enhancement comparison vectors are extracted from the global inter-class signal focus linkage vectors that have undergone knowledge interaction and improvement.

[0194] In this way, by building an interactive knowledge fusion platform, efficient knowledge interaction of global inter-class signal focus linkage vectors under multiple classification clusters is achieved. Through dynamic correlation analysis, information interaction and fusion, and adaptive adjustment, not only the accuracy and completeness of the global inter-class signal focus linkage vector are improved, but also a richer data foundation is provided for subsequent signal processing and meteorological analysis.

[0195] In detail, the technical core of the above-mentioned independent embodiment is to build an interactive knowledge fusion platform, through which the knowledge interaction of global inter-class signal focusing linkage vectors under multiple classification clusters is realized. First, the signal enhancement system builds an interactive knowledge fusion platform. This platform supports multimodal data interaction and dynamic knowledge graph construction, and provides strong technical support for the processing of global inter-class signal focusing linkage vectors. Next, the system loads the global inter-class signal focusing linkage vectors under several classification clusters into the interactive knowledge fusion platform. These vectors form initialized knowledge nodes in the platform, and each node represents a specific meteorological signal state or feature. Then, using the interactive mechanism of the platform, the signal enhancement system performs dynamic association analysis on each knowledge node. The purpose of this step is to identify and establish a similarity network between nodes. Through this network, the system can clearly see the connection and difference between the global inter-class signal focusing linkage vectors under different classification clusters. Based on the similarity network, the system performs information interaction and fusion of global inter-class signal focusing linkage vectors across classification clusters. This means that the knowledge under different classification clusters can learn from and enhance each other, thereby improving the accuracy and completeness of the global inter-class signal focusing linkage vector. In addition, through the platform's dynamic optimization algorithm, the signal enhancement system will also adaptively adjust and improve the global inter-class signal focus linkage vector after interaction. This step aims to ensure the accuracy and consistency of information, so that the global inter-class signal focus linkage vector finally extracted is more in line with the actual meteorological conditions. Finally, from the global inter-class signal focus linkage vector that has undergone knowledge interaction and improvement, the signal enhancement system extracts the global inter-class signal focus linkage vector corresponding to each group of signal enhancement comparison vectors. These vectors not only contain rich meteorological information, but also have high accuracy and completeness, providing a richer data basis for subsequent signal processing and meteorological analysis. In summary, by building an interactive knowledge fusion platform, the signal enhancement system realizes efficient knowledge interaction of global inter-class signal focus linkage vectors under multiple classification clusters. This technical solution not only improves the accuracy and completeness of the global inter-class signal focus linkage vector, but also provides more reliable data support for subsequent signal processing and meteorological analysis. This means that in the face of complex and changing meteorological conditions, it is possible to more accurately grasp and predict the changing trend of meteorological signals, thereby making more scientific and reasonable decisions.

[0196] In summary, in the field of meteorology, using an exemplary neural network algorithm to mine feature vectors of raw lidar data and its related data can provide a deep understanding and analysis of meteorological phenomena. The following are four different examples of neural network algorithms to mine four different feature vectors:

[0197] 1) Mining of original signal state monitoring vector

[0198] Algorithm Example: Convolutional Neural Network (CNN)

[0199] Application: Use CNN's spatial feature extraction capability to process raw lidar data.

[0200] Steps: Convert the raw LiDAR data into image form as the input of CNN; extract the spatial features of the data through multiple convolutional layers; use pooling layers to reduce the data dimension while retaining important features; map the extracted features to the original signal state monitoring vector through a fully connected layer.

[0201] 2) Mining of spatiotemporal linkage vectors of laser point clouds

[0202] Algorithm example: Long short-term memory network (LSTM) combined with CNN

[0203] Application: LSTM is used to process time series data and can be combined with CNN to capture spatiotemporal features.

[0204] Steps: Use CNN to extract the spatial features of the original point cloud detection data; use the output of CNN as the input of LSTM to capture changes in the time series; the output of LSTM is the spatiotemporal linkage vector of the laser point cloud.

[0205] 3) Mining of signal-noise change trend vector

[0206] Algorithm Example: Recurrent Neural Network (RNN) Variant - Gated Recurrent Unit (GRU)

[0207] Application: GRU is suitable for processing sequence data and can capture long-term dependencies in the sequence.

[0208] Steps: Input several original lidar data segments into the GRU network in sequence; GRU learns and outputs the internal state of each data segment to reflect the signal-noise change trend; and obtains the signal-noise change trend vector through these internal states.

[0209] 4) Mining of Quantitative Structure Geometric Distribution Vectors

[0210] Algorithm Example: Graph Neural Network (GNN)

[0211] Application: GNN is suitable for processing graph structured data and can learn the relationship between nodes.

[0212] Steps: Convert the hypertable structure model data corresponding to the surface performance mapping information into a graph structure; use GNN to learn the associations and features between nodes; and process the output of GNN to obtain a quantitative structural geometric distribution vector.

[0213] The above four neural network algorithms mine different types of feature vectors, which helps to more comprehensively understand and analyze the complex patterns and associations in meteorological data. Through these methods, lidar data and related data can be used more effectively to improve the accuracy and efficiency of meteorological forecasts.

[0214] Further, Figure 2 FIG. 2 is a schematic diagram of a signal enhancement system 200 provided in an embodiment of the present application. Figure 2 The signal enhancement system 200 shown includes a processor 210, and the processor 210 can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0215] Alternatively, if Figure 2 As shown, the signal enhancement system 200 may further include a memory 230. The processor 210 may call and run a computer program from the memory 230 to implement the method in the embodiment of the present application.

[0216] The memory 230 may be a separate device independent of the processor 210 , or may be integrated into the processor 210 .

[0217] Alternatively, if Figure 2 As shown, the signal enhancement system 200 may further include a transceiver 220, and the processor 210 may control the transceiver 220 to interact with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices.

[0218] Optionally, the signal enhancement system 200 may implement the corresponding processes corresponding to the storage engine or components in the storage engine (such as a processing module) or a device deployed with a storage engine in each method of the embodiments of the present application, which will not be described in detail here for the sake of brevity.

[0219] It should be understood that the processor of the embodiment of the present application may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method embodiment can be completed by the hardware integrated logic circuit or software instructions in the processor. The above processor can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor are combined and performed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0220] It can be understood that the memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0221] It should be understood that the above-mentioned memory is exemplary but not restrictive. For example, the memory in the embodiments of the present application may also be static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is to say, the memory in the embodiments of the present application is intended to include but not limited to these and any other suitable types of memory.

[0222] Based on the above, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program implements the above method when running.

[0223] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations.

Claims

1. A laser radar signal enhancement method based on artificial intelligence optimization, characterized in that: Applied to a signal enhancement system, the method comprises: Performing feature vector mining on the original laser radar data to obtain an original signal state monitoring vector of the original laser radar data; Performing feature vector mining on the original point cloud detection data corresponding to the original laser radar data to obtain a laser point cloud spatiotemporal linkage vector of the original point cloud detection data; Performing feature vector mining on a plurality of original laser radar data segments corresponding to the original laser radar data to obtain a signal-to-noise change trend vector corresponding to each of the original laser radar data segments; Performing feature vector mining on a plurality of hypertable structure model data corresponding to the surface performance mapping information to obtain a quantized structural geometric distribution vector corresponding to each group of the hypertable structure model data; For each group of the quantized structure geometric distribution vectors, the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, a plurality of the signal-to-noise change trend vectors and the quantized structure geometric distribution vector are subjected to knowledge interaction based on inter-class feature focusing to obtain a signal enhancement comparison vector; Structural parameter prediction is performed on a plurality of the signal enhancement comparison vectors to obtain hypersurface geometric parameters that match both the original lidar data and the surface performance mapping information.

2. The method according to claim 1, characterized in that The performing feature vector mining on a plurality of original laser radar data segments corresponding to the original laser radar data to obtain a signal-to-noise change trend vector corresponding to each of the original laser radar data segments includes: For each of the original laser radar data segments, feature vector mining is performed on the original laser radar data segment according to the first knowledge dimension to obtain a first signal quality assessment vector corresponding to the original laser radar data segment; Performing feature vector mining on the original laser radar data segment according to the second knowledge dimension to obtain a second signal quality assessment vector corresponding to the original laser radar data segment; Knowledge interaction is performed on the first signal quality assessment vector and the second signal quality assessment vector to obtain a signal-to-noise change trend vector corresponding to the original lidar data segment.

3. The method according to claim 1 or 2, characterized in that: The steps of obtaining the plurality of original laser radar data segments include: The original laser radar data is disassembled based on a data scanning core to obtain the plurality of original laser radar data segments; each of the original laser radar data segments includes key field indexes of the associated plurality of original laser radar data segments.

4. The method according to claim 1, characterized in that: The method of performing feature vector mining on a plurality of hypertable structure model data corresponding to the surface performance mapping information to obtain a quantized structure geometric distribution vector corresponding to each group of the hypertable structure model data includes: For each group of the hypertable structure model data, identifying the spatial arrangement state of the hypertable structure model data to obtain a target spatial arrangement state information set corresponding to the hypertable structure model data; Feature vector mining is performed on the target space arrangement state information set to obtain the quantitative structure geometric distribution vector corresponding to the hypertable structure model data.

5. The method according to claim 4, characterized in that The performing feature vector mining on the target spatial arrangement state information set to obtain the quantized structural geometric distribution vector corresponding to the hypertable structural model data includes: Performing knowledge mapping on the target spatial arrangement state information set to obtain a plurality of first spatial arrangement state knowledge corresponding to the target spatial arrangement state information set; Performing interval numerical mapping on the plurality of first spatial arrangement state knowledge to obtain second spatial arrangement state knowledge corresponding to each first spatial arrangement state knowledge; Performing feature collision on a plurality of pieces of the second spatial arrangement state knowledge to obtain third spatial arrangement state knowledge corresponding to each piece of the second spatial arrangement state knowledge; Linearly quantize a plurality of the third spatial arrangement state knowledge to obtain the quantized structure geometric distribution vector.

6. The method according to claim 1, characterized in that For each group of the quantized structure geometric distribution vectors, the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, a plurality of the signal-to-noise change trend vectors and the quantized structure geometric distribution vector are subjected to knowledge interaction based on inter-class feature focusing to obtain a signal enhancement comparison vector, including: Performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, and a plurality of the signal-to-noise change trend vectors to obtain a first inter-class signal focusing linkage vector; For each group of the quantization structure geometric distribution vectors, knowledge interaction is performed on the first inter-class signal focus linkage vector and the quantization structure geometric distribution vector to obtain the signal enhancement comparison vector.

7. The method according to claim 1, characterized in that For each group of the quantized structure geometric distribution vectors, the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, a plurality of the signal-to-noise change trend vectors and the quantized structure geometric distribution vector are subjected to knowledge interaction based on inter-class feature focusing to obtain a signal enhancement comparison vector, including: Performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, and a plurality of the signal-to-noise change trend vectors to obtain a first inter-class signal focusing linkage vector; For each group of the quantized structure geometric distribution vectors, the original signal state monitoring vector and the quantized structure geometric distribution vector are subjected to knowledge interaction based on inter-class feature focusing to obtain a second inter-class signal focusing linkage vector; Performing knowledge interaction on the first inter-class signal focus linkage vector and the second inter-class signal focus linkage vector to obtain the signal enhancement comparison vector; The step of performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector, the laser point cloud spatiotemporal linkage vector, and a plurality of the signal-to-noise change trend vectors to obtain a first inter-class signal focusing linkage vector includes: Performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector and the laser point cloud spatiotemporal linkage vector to obtain a third inter-class signal focusing linkage vector; Performing knowledge interaction based on inter-class feature focusing on the original signal state monitoring vector and the plurality of signal-to-noise change trend vectors to obtain a fourth inter-class signal focusing linkage vector; Knowledge interaction is performed on the third inter-class signal focusing linkage vector and the fourth inter-class signal focusing linkage vector to obtain the first inter-class signal focusing linkage vector; the knowledge size of the first inter-class signal focusing linkage vector, the knowledge size of the third inter-class signal focusing linkage vector, and the knowledge size of the fourth inter-class signal focusing linkage vector are the same.

8. The method according to claim 6, characterized in that The performing knowledge interaction on the first inter-class signal focusing linkage vector and the quantization structure geometric distribution vector to obtain the signal enhancement comparison vector includes: Performing knowledge interaction based on inter-class feature focusing on the first inter-class signal focusing linkage vector and the quantization structure geometric distribution vector to obtain a target signal quality deduction vector; Knowledge interaction is performed on the first inter-class signal focus linkage vector and the target signal quality deduction vector to obtain the signal enhancement comparison vector.

9. The method according to claim 1, characterized in that: The step of predicting structural parameters of the plurality of signal enhancement comparison vectors to obtain hypersurface geometric parameters that match both the original laser radar data and the surface performance mapping information includes: Performing signal stream integration on a plurality of the signal enhancement comparison vectors to obtain a global inter-class signal focusing linkage vector corresponding to each group of the signal enhancement comparison vectors; Predicting structural parameters of a plurality of the global inter-class signal focusing linkage vectors to obtain the hypersurface geometric parameters; The performing signal stream integration on a plurality of the signal enhancement comparison vectors to obtain a global inter-class signal focusing linkage vector corresponding to each group of the signal enhancement comparison vectors includes: Performing clustering processing on the plurality of signal enhancement comparison vectors to obtain a plurality of signal enhancement comparison vectors under a plurality of classification clusters; For the plurality of signal enhancement comparison vectors under each classification cluster, signal stream integration is performed on the plurality of signal enhancement comparison vectors under the classification cluster to obtain a global inter-class signal focusing linkage vector corresponding to each group of the signal enhancement comparison vectors under the classification cluster; Knowledge interaction is performed on a plurality of the global inter-class signal focusing linkage vectors under a plurality of the classification clusters to obtain a global inter-class signal focusing linkage vector corresponding to each group of the signal enhancement comparison vectors.

10. A signal enhancement system, characterized in that: The method comprises at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method according to any one of claims 1 to 9.

Images