Geographic surveying and mapping data real-time updating method based on adaptive algorithm

Abstract

The invention relates to a geographic surveying and mapping data real-time updating method based on an adaptive algorithm, which comprises the following steps of: deploying a widely distributed sensor network to collect geographic data in real time, performing primary processing by utilizing edge calculation, and transmitting the data through a wireless communication technology; dynamically adjusting learning rate parameters by using an adaptive time-varying learning rate optimization algorithm; simulating geographic data change by adopting a generative adversarial network model and fusing generated data and actual data; performing Bayesian network fusion on different sensor data; processing the geographic data in parallel by using a quantum state superposition optimization algorithm; and updating the processed and fused geographic data to a geographic information system in real time, and performing visual display. According to the method, the real-time performance, the accuracy and the diversity of geographic data are improved through a self-adaptive algorithm, quantum calculation and a big data technology.

Description

Technical Field

[0001] The invention relates to the technical field of geographic information systems, and in particular to a real-time updating method for geographic surveying and mapping data based on an adaptive algorithm. Background Art

[0002] Existing geographic surveying and mapping data processing methods mainly rely on traditional manual data collection and processing, which usually requires a long period of time to complete data collection, processing and updating. This method is not only inefficient, but also difficult to cope with the real-time changes of geographic information in a dynamic environment, resulting in data lag and failure to provide accurate information support in a timely manner. In addition, when processing multi-source data, existing technologies often use simple data fusion methods, which makes it difficult to effectively integrate data from different sensors, resulting in low comprehensiveness and consistency of data.

[0003] With the development of Internet of Things technology, sensor networks have been widely used in the field of geographic surveying and mapping. By deploying a large number of sensors, a large amount of geographic data can be collected in real time. However, this also brings huge challenges to data processing. When processing massive data, existing technologies usually adopt centralized data processing methods, which requires all data to be transmitted to the central processing center for processing, which not only increases the burden of data transmission, but also has bottlenecks in processing speed and efficiency.

[0004] As an emerging computing model, edge computing technology can effectively reduce the burden of data transmission and improve the efficiency of data processing by performing preliminary data processing on sensor nodes or edge devices. However, existing edge computing methods still have insufficient processing power when processing complex geographic data, making it difficult to meet the requirements of high precision and real-time performance.

[0005] In order to improve the efficiency of geographic data processing, generative adversarial network technology has been introduced into the field of geographic surveying and mapping data processing in recent years. Generative adversarial network technology can generate simulated data similar to actual data by simulating the changes in geographic data, and integrate it with actual data to improve the authenticity and diversity of the data. However, the existing generative adversarial network technology models often face problems such as model instability, long training time and high consumption of computing resources during training and application.

[0006] As a cutting-edge computing technology, quantum computing technology has huge parallel computing capabilities and can significantly improve the speed and efficiency of geographic data processing. In particular, quantum state superposition and quantum error correction technology can improve the stability and reliability of geographic data processing through quantum state parallel processing and error correction mechanisms. However, the current quantum computing technology still has certain technical difficulties and implementation barriers in practical applications.

[0007] In view of the defects of the above-mentioned prior art, the present invention proposes a real-time update method for geographic surveying and mapping data based on an adaptive algorithm. First, by deploying a widely distributed sensor network, geographic data is collected in real time, and edge computing is used for preliminary processing, and the data is transmitted to the data processing center through wireless communication technology. An adaptive time-varying learning rate optimization algorithm is used to dynamically adjust the learning rate parameters by monitoring the change rate and fluctuation of geographic data to improve the accuracy and efficiency of data processing.

[0008] Secondly, the present invention adopts a generative adversarial network model to simulate the changes in geographic data, fuse the generated data with the actual data, and improve the authenticity and diversity of the data. For data from different sensors, the Bayesian network fusion method is used to perform comprehensive processing based on the prior probability and conditional probability of the data source, solving the problem of difficulty in multi-source data fusion.

[0009] In addition, the quantum state superposition optimization algorithm is combined with quantum interference optimization and error correction technology to process geographic data in parallel through quantum superposition states, thereby improving the stability and reliability of data processing. Finally, the processed and fused geographic data is updated in real time to the geographic information system, and the real-time updated geographic data is visualized.

[0010] Through the above innovations, the present invention improves the processing efficiency of geographic surveying and mapping data while significantly improving the accuracy and real-time performance of the data, overcomes the main defects in the prior art, and has broad application prospects. Summary of the invention

[0011] One object of the present invention is to propose a real-time updating method for geographic surveying and mapping data based on an adaptive algorithm. The method makes full use of adaptive algorithms, generative adversarial networks, quantum computing, big data processing, edge computing, wireless communication technology and Bayesian networks. The process of real-time collection of geographic data through a sensor network, preliminary processing using edge computing, wireless transmission, adaptive time-varying learning rate optimization, generative adversarial network fusion, quantum state superposition optimization and Bayesian network fusion is described in detail. The method has the advantages of high real-time performance, high processing efficiency, strong multi-source data fusion capability, and high data accuracy and reliability.

[0012] According to an embodiment of the present invention, a method for real-time updating of geographic surveying and mapping data based on an adaptive algorithm comprises the following steps: S1. Deploy a widely distributed sensor network to collect geographic data in real time; S2, transmitting the data to a data processing center; S3, using an adaptive time-varying learning rate optimization algorithm to dynamically adjust the learning rate parameters by monitoring the rate of change and fluctuation of geographic data; S4, using the generative adversarial network model to simulate the changes in geographic data and fuse the generated data with the actual data; S5. For geographic data from different sensors, a Bayesian network fusion method is used to perform comprehensive processing based on the prior probability and conditional probability of the data source; S6. Use quantum state superposition optimization algorithm combined with quantum interference optimization and error correction technology to process geographic data in parallel through quantum superposition state; S7, updating the processed and integrated geographic data to the geographic information system in real time; S8. Visualize the real-time updated geographic data.

[0013] Optionally, the S1 includes the following steps: S11, select multiple sensor installation locations in the target area, and the sensor network coverage is wide and evenly distributed; S12. Choose according to terrain, environment and surveying requirements. sensor, sensors, photogrammetric sensors, and meteorological sensors; S13, installing the sensor at the predetermined position, and the sensor is firmly fixed and operates normally; S14, configuring the working parameters of the sensor, including sampling frequency, data transmission frequency and data format; S15, start the sensor network, collect geographic data in real time, and transmit the data to the edge computing device through the wireless communication module; S16. Monitor the operating status of the sensor network, regularly calibrate and maintain sensors, and ensure the accuracy and continuity of data collection.

[0014] Optionally, S2 includes the following steps: S21, deploy edge computing devices on sensor nodes to perform preliminary processing on real-time collected geographic data; S22. Use edge computing devices to pre-process data, including data cleaning, data filtering, and data compression.

[0015] Optionally, S3 includes the following steps: S31. Use sliding window technology to process geographic data in segments and set the size of the sliding window ,in The size is determined according to the frequency of data collection and update requirements; S32. Calculate the geographic data change rate in each sliding window and fluctuations ,in: For the The standard deviation of the data in the sliding window; S33, set the initial learning rate and adjustment factor , through the formula: Dynamically adjust learning rate ,in For the The learning rate of the iteration, To avoid division by zero, use a very small constant; S34, use the adaptive time-varying learning rate optimization algorithm to iteratively process the geographic data. In each iteration, the learning rate parameter is updated according to the data change rate and fluctuation in the current sliding window. ; S35. In each iteration, calculate the gradient of data processing , combined with adaptive learning rate Update model parameters ; S36, using dynamic gradient pruning technology, in each iteration, select and retain important gradient paths according to the gradient size, prune unimportant gradients, and reduce the amount of calculation: ; in, For the parameters, is the gradient pruning threshold; S37. During the data processing, the learning rate adjustment effect is monitored in real time, and the adjustment strategy is further optimized based on the real-time monitoring data: ; in, is the adjustment factor, The final adjusted learning rate is applied to the processing and analysis of geographic data.

[0016] Optionally, S4 includes the following steps: S41. Construct a generative adversarial network model, including a generative network and a discriminative network. The input of the generative network is a noise vector , the output is simulated geographic data , the input of the discriminant network is the actual geographic data and generate data , the output is the judgment result and ; S42. Initialize the parameters of the generation network and the discrimination network and , set the initial learning rate and , and the number of training rounds and batch size ; S43. For each training round , perform the following steps: S431, generate noise vector by sampling from noise distribution , and input the generated network to generate simulated geographic data ; S432. Randomly sample real data from actual geographic data distribution ; S433. Calculate the loss function of the discriminant network : ; in, represents the discriminant network, Indicates A sample of actual data, represents the generative network, Indicates A noise vector, Indicates the batch size; S434, use stochastic gradient descent method to update the parameters of the discriminant network : ; in, represents the parameters of the discriminant network, represents the learning rate, Represents the discriminant network loss function about The gradient of S435. Calculate the loss function of the generated network : ; in, represents the loss function of the generated network, Indicates A noise vector, Indicates the batch size; S436, use stochastic gradient descent method to update the parameters of the generated network : ; in, To generate the parameters of the network, To generate the network loss function about The gradient of S44. During the training process, data is generated by calculation and actual data The mean square error is: ; Among them, the mean square error is a measure of the difference between the generated data and the actual data. is the sample size, For the A sample of actual data, Generate the network generated simulated data samples, Indicates A noise vector; S45. After training is completed, use the generated data and actual data Fusion strategy, calculate the fusion data after weight optimization : S451, calculation and generation of data and actual data Statistical properties of , and variance , ; S452. Determine weight and , so that the fusion data The statistical properties of are close to those of the actual data: ; ; in, and are the mean and variance of the fused data respectively, satisfying and ; S453, by minimizing the following loss function Determining the optimal weights and : ; Among them, the mean , is the mean, , is the variance, and are the mean and variance of the fused data respectively; S454, use gradient descent method to optimize weights and : ; ; in, and is the weight of generated data and actual data, is the loss function for weight optimization, The learning rate optimized for the weights; S46. The fused geographic data Input into subsequent data processing and analysis process.

[0017] Optionally, S5 includes the following steps: S51. Collect data from different sensors, including data, data, photogrammetric data, and meteorological data; S52, preprocess the data of each sensor and extract feature vectors ; S53. Establishing Bayesian network model , defines the prior probability of each data source and conditional probability, ,in Represents different data sources; S54. Calculate the dynamic prior probability of each data source , based on the weighted fusion of historical data and real-time data: ; in, is the weighting coefficient, is the prior probability of historical data, is the prior probability of real-time data; S55. Calculate conditional probability When , an adaptive parameter adjustment mechanism is introduced to dynamically adjust according to the correlation between data sources: ; ; in, For data source and The correlation coefficient between Data Source The standard deviation of For data source The standard deviation of S56. Comprehensively process data from different sensors and use enhanced Bayesian inference methods to calculate fused geographic data : ; in, is the fused geographic data. For data from different sensors; S57, introduce a dynamic adjustment mechanism to maximize the posterior probability , optimize the fused geographic data : ; in, The dynamic weight coefficient for each data source is adjusted according to the reliability and real-time performance of the data source; S58. The fused geographic data Input into subsequent data processing and analysis process.

[0018] Optionally, the S6 includes the following steps: S61. Quantum state initialization and encoding: Constructing the initial quantum state and encoding multi-source geographic data Dynamically encoded as quantum states : ; in, and According to geographic data characteristics and Dynamically adjusted amplitude coefficients satisfy the normalization condition: ; S62, Quantum state adaptive filtering and error correction: Combining quantum adaptive filtering and error correction mechanism: ; ; in, is the quantum state adaptive filtering operator, is the quantum error correction operator, is the filtering parameter, is the learning rate, is the loss function, and are the weight and adjustment value of the feedback error respectively; S63. Multi-source data quantum fusion: Using the superposition characteristics of quantum states, geographic data from different sources are integrated into one quantum state: ; in, is a quantum method operator for multi-source data fusion, is the corresponding data fusion parameter; S64, Quantum Phase Change Optimization: Introducing quantum phase change detection and optimization to identify key changes in geographic data and optimize processing: ; ; in, Optimizing operators for quantum phase transitions, To optimize the parameters, is the phase change detection parameter, Optimize the step size for phase transition, To optimize the objective function, and , are the weight and adjustment value of the optimized feedback error respectively; S65, Adaptive feedback control: Use the adaptive feedback control mechanism to monitor and adjust processing parameters in real time and optimize the data processing process: ; in, , is the learning rate, is the feedback control function, and are the weight and adjustment value of the feedback error respectively; S66. Quantum state measurement and result generation: Perform quantum measurement on the optimized quantum state to obtain optimized geographic data: ; in, It is the measurement operator used to convert quantum states into classical data.

[0019] Optionally, the S7 includes the following steps: S71, pre-processing the processed and fused geographic data, and using an adaptive noise filtering algorithm to eliminate noise and outliers; S72, compressing the preprocessed geographic data, using a dynamic compression ratio adjustment algorithm to dynamically adjust the compression ratio according to data characteristics; S73, encrypting the compressed geographic data; S74, transmitting the encrypted geographic data to the geographic information system through a secure communication channel; S75, decrypting the received geographic data at the geographic information system end, and restoring the original state of the data using a quantum decryption algorithm; S76, decompressing the decrypted geographic data and restoring complete information of the data using an adaptive decompression algorithm; S77. Update the decompressed geographic data to the geographic information system in real time, and use an adaptive update algorithm to dynamically adjust the update strategy according to changes in real-time data.

[0020] Optionally, the S8 includes the following steps: S81. Convert real-time updated geographic data into a format suitable for visual display, using data normalization and standardization; S82, performing three-dimensional modeling on the converted geographic data, using a grid-based modeling technology to generate a three-dimensional geographic model; S83, performing texture mapping on the three-dimensional geographic model; S84. Interactive design of textured three-dimensional geographic models using virtual reality and augmented reality technologies; S85, performing real-time rendering of the interactive three-dimensional geographic model using a graphics rendering engine; S86: Visually display the real-time rendered geographic image on the user terminal to achieve real-time visual display of geographic data.

[0021] The beneficial effects of the present invention are: The real-time updating method of geographic surveying and mapping data based on adaptive algorithm proposed in the present invention overcomes many defects in the prior art and achieves the following beneficial effects: Improve real-time performance: Using widely distributed sensor networks and edge computing technology, real-time collection and preliminary processing of geographic data are achieved, which significantly reduces the delay of data transmission and processing and improves the real-time performance of geographic data. Through wireless communication technology, geographic data is transmitted in real time, so that data can be quickly delivered to the data processing center, ensuring the timeliness and accuracy of the data.

[0022] Improve processing efficiency: Adopting adaptive time-varying learning rate optimization algorithm, by monitoring the change rate and fluctuation of geographic data, dynamically adjusting the learning rate parameters, improves the efficiency and accuracy of data processing. The adaptive algorithm can flexibly adjust the processing strategy to adapt to the real-time changes of data, improving processing efficiency and accuracy Enhanced data fusion capability: Generate adversarial networks to simulate geographic data changes, fuse generated data with actual data, and improve the authenticity and diversity of data. Use Bayesian network fusion method to perform comprehensive processing based on the prior probability and conditional probability of data sources, achieve efficient fusion of multi-source data, and improve the comprehensiveness and consistency of data.

[0023] Ensure data processing stability and reliability: Using quantum state superposition optimization algorithm combined with quantum interference optimization and error correction technology, geographic data is processed in parallel through quantum superposition state, which improves the stability and reliability of data processing. The parallel processing capability of quantum computing significantly improves the speed and accuracy of data processing, while quantum error correction technology ensures the stability of data processing.

[0024] Realize data visualization: Update the processed and integrated geographic data to the geographic information system in real time, and visualize the updated geographic data. Through high-performance graphics rendering engine and virtual reality and augmented reality technology, provide intuitive three-dimensional geographic data display and interactive functions, and enhance users' understanding and application capabilities of geographic information. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 The overall flow chart of a method for real-time updating of geographic surveying and mapping data based on an adaptive algorithm proposed by the present invention; Figure 2 A simplified flow chart of an adaptive time-varying learning rate optimization and generative adversarial network model for geographic surveying and mapping data based on an adaptive algorithm proposed by the present invention; DETAILED DESCRIPTION The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0026] refer to Figure 1-2 , a real-time updating method for geographic surveying and mapping data based on an adaptive algorithm, comprising the following steps: S1. Deploy a widely distributed sensor network to collect geographic data in real time; S2, transmitting the data to a data processing center; S3, using an adaptive time-varying learning rate optimization algorithm to dynamically adjust the learning rate parameters by monitoring the rate of change and fluctuation of geographic data; S4, using the generative adversarial network model to simulate the changes in geographic data and fuse the generated data with the actual data; S5. For geographic data from different sensors, a Bayesian network fusion method is used to perform comprehensive processing based on the prior probability and conditional probability of the data source; S6. Use quantum state superposition optimization algorithm combined with quantum interference optimization and error correction technology to process geographic data in parallel through quantum superposition state; S7, updating the processed and integrated geographic data to the geographic information system in real time; S8. Visualize the real-time updated geographic data.

[0027] In this implementation, S1 includes the following steps: S11, select multiple sensor installation locations in the target area, and the sensor network coverage is wide and evenly distributed; S12. Choose according to terrain, environment and surveying requirements. sensor, sensors, photogrammetric sensors, and meteorological sensors; S13, installing the sensor at the predetermined position, and the sensor is firmly fixed and operates normally; S14, configuring the working parameters of the sensor, including sampling frequency, data transmission frequency and data format; S15, start the sensor network, collect geographic data in real time, and transmit the data to the edge computing device through the wireless communication module; S16. Monitor the operating status of the sensor network, regularly calibrate and maintain sensors, and ensure the accuracy and continuity of data collection.

[0028] In this implementation, S2 includes the following steps: S21, deploy edge computing devices on sensor nodes to perform preliminary processing on real-time collected geographic data; S22. Use edge computing devices to pre-process data, including data cleaning, data filtering, and data compression; In this implementation, S3 includes the following steps: S31. Use sliding window technology to process geographic data in segments and set the size of the sliding window ,in The size is determined according to the frequency of data collection and update requirements; S32. Calculate the geographic data change rate in each sliding window and fluctuations ,in: For the The standard deviation of the data in the sliding window; S33, set the initial learning rate and adjustment factor , through the formula: Dynamically adjust learning rate ,in For the The learning rate of the iteration, To avoid division by zero, use a very small constant; S34, use the adaptive time-varying learning rate optimization algorithm to iteratively process the geographic data. In each iteration, the learning rate parameter is updated according to the data change rate and fluctuation in the current sliding window. ; S35. In each iteration, calculate the gradient of data processing , combined with adaptive learning rate Update model parameters ; S36, using dynamic gradient pruning technology, in each iteration, select and retain important gradient paths according to the gradient size, prune unimportant gradients, and reduce the amount of calculation: ; in, For the parameters, is the gradient pruning threshold; S37. During the data processing, the learning rate adjustment effect is monitored in real time, and the adjustment strategy is further optimized based on the real-time monitoring data: ; in, is the adjustment factor, The final adjusted learning rate is applied to the processing and analysis of geographic data.

[0029] In this implementation, S4 includes the following steps: S41. Construct a generative adversarial network model, including a generative network and a discriminative network. The input of the generative network is a noise vector , the output is simulated geographic data , the input of the discriminant network is the actual geographic data and generate data , the output is the judgment result and ; S42. Initialize the parameters of the generation network and the discrimination network and , set the initial learning rate and , and the number of training rounds and batch size ; S43. For each training round , perform the following steps: S431, generate noise vector by sampling from noise distribution , and input the generated network to generate simulated geographic data ; S432. Randomly sample real data from actual geographic data distribution ; S433. Calculate the loss function of the discriminant network : ; in, represents the discriminant network, Indicates A sample of actual data, represents the generative network, Indicates A noise vector, Indicates the batch size; S434, use stochastic gradient descent method to update the parameters of the discriminant network : ; in, represents the parameters of the discriminant network, represents the learning rate, Represents the discriminant network loss function about The gradient of S435. Calculate the loss function of the generated network : ; in, represents the loss function of the generated network, Indicates A noise vector, Indicates the batch size; S436, use stochastic gradient descent method to update the parameters of the generated network : ; in, To generate the parameters of the network, To generate the network loss function about The gradient of S44. During the training process, data is generated by calculation and actual data The mean square error is: ; Monitor the similarity between the generated data and the actual data, and adjust the noise vector Distribution of S45. After training is completed, use the generated data and actual data Fusion strategy, calculate the fusion data after weight optimization : S451, calculation and generation of data and actual data Statistical properties of , and variance , ; S452. Determine weight and , so that the fusion data The statistical properties of are close to those of the actual data: ; ; in, and are the mean and variance of the fused data respectively, satisfying and ; S453, by minimizing the following loss function Determining the optimal weights and : ; Among them, the mean , is the mean, , is the variance, and are the mean and variance of the fused data respectively; S454, use gradient descent method to optimize weights and : ; ; in, and is the weight of generated data and actual data, is the loss function for weight optimization, The learning rate optimized for the weights; S46. The fused geographic data Input into subsequent data processing and analysis process.

[0030] S51. Collect data from different sensors, including data, data, photogrammetric data, and meteorological data; S52, preprocess the data of each sensor and extract feature vectors ; S53. Establishing Bayesian network model , defines the prior probability of each data source and conditional probability, ,in Represents different data sources; S54. Calculate the dynamic prior probability of each data source , based on the weighted fusion of historical data and real-time data: ; in, is the weighting coefficient, is the prior probability of historical data, is the prior probability of real-time data; S55. Calculate conditional probability When , an adaptive parameter adjustment mechanism is introduced to dynamically adjust according to the correlation between data sources: ; ; in, For data source and The correlation coefficient between Data Source The standard deviation of For data source The standard deviation of S56. Comprehensively process data from different sensors and use enhanced Bayesian inference methods to calculate fused geographic data : ; in, is the fused geographic data. For data from different sensors; S57, introduce a dynamic adjustment mechanism to maximize the posterior probability , optimize the fused geographic data : ; in, The dynamic weight coefficient for each data source is adjusted according to the reliability and real-time performance of the data source; S58. The fused geographic data Input into subsequent data processing and analysis process.

[0031] In this implementation, S6 includes the following steps: S61. Quantum state initialization and encoding: Constructing the initial quantum state and encoding multi-source geographic data Dynamically encoded as quantum states : ; in, and According to geographic data characteristics and Dynamically adjusted amplitude coefficients satisfy the normalization condition: ; S62, Quantum state adaptive filtering and error correction: Combining quantum adaptive filtering and error correction mechanism: ; ; in, is the quantum state adaptive filtering operator, is the quantum error correction operator, is the filtering parameter, is the learning rate, is the loss function, and are the weight and adjustment value of the feedback error respectively; S63. Multi-source data quantum fusion: Using the superposition characteristics of quantum states, geographic data from different sources are integrated into one quantum state: ; in, is a quantum method operator for multi-source data fusion, is the corresponding data fusion parameter; S64, Quantum Phase Change Optimization: Introducing quantum phase change detection and optimization to identify key changes in geographic data and optimize processing: ; ; in, Optimizing operators for quantum phase transitions, To optimize the parameters, is the phase change detection parameter, Optimize the step size for phase transition, To optimize the objective function, and , are the weight and adjustment value of the optimized feedback error respectively; S65, Adaptive feedback control: Use the adaptive feedback control mechanism to monitor and adjust processing parameters in real time and optimize the data processing process: ; in, , is the learning rate, is the feedback control function, and are the weight and adjustment value of the feedback error respectively; S66. Quantum state measurement and result generation: Perform quantum measurement on the optimized quantum state to obtain optimized geographic data: ; in, It is the measurement operator used to convert quantum states into classical data.

[0032] In this implementation, S7 includes the following steps: S71, pre-processing the processed and fused geographic data, and using an adaptive noise filtering algorithm to eliminate noise and outliers; S72, compressing the preprocessed geographic data, using a dynamic compression ratio adjustment algorithm to dynamically adjust the compression ratio according to data characteristics; S73, encrypting the compressed geographic data; S74, transmitting the encrypted geographic data to the geographic information system through a secure communication channel; S75, decrypting the received geographic data at the geographic information system end, and restoring the original state of the data using a quantum decryption algorithm; S76, decompressing the decrypted geographic data and restoring complete information of the data using an adaptive decompression algorithm; S77. Update the decompressed geographic data to the geographic information system in real time, and use an adaptive update algorithm to dynamically adjust the update strategy according to changes in real-time data.

[0033] In this implementation, S8 includes the following steps: S81. Convert real-time updated geographic data into a format suitable for visual display, using data normalization and standardization; S82, performing three-dimensional modeling on the converted geographic data, using a grid-based modeling technology to generate a three-dimensional geographic model; S83, performing texture mapping on the three-dimensional geographic model; S84. Interactive design of textured three-dimensional geographic models using virtual reality and augmented reality technologies; S85. Rendering the interactive three-dimensional geographic model in real time; S86: Visually display the real-time rendered geographic image on the user terminal to achieve real-time visual display of geographic data.

[0034] Embodiment 1: A real-time update method for geographic surveying and mapping data based on an adaptive algorithm is applied in a smart city project. The project aims to improve the efficiency and responsiveness of urban management in the 25 square kilometer area, covering multiple commercial centers, office buildings and residential areas. The core goal of the project is to achieve real-time geographic data collection and processing to support urban planning, traffic management, environmental monitoring and emergency response.

[0035] exist We first deployed a widely distributed sensor network in the domain. These sensors include sensor, Sensors, photogrammetry sensors and meteorological sensors are installed on building roofs, traffic intersections and public facilities, covering a wide range and evenly distributed. The sensors collect geographic data in real time, including location information, height information, image data and meteorological data.

[0036] The data collected by the sensor network is transmitted to the edge computing device through the wireless communication module for preliminary processing. The edge computing device cleans, filters and compresses the data, and transmits it to the main server located in the data processing center through a secure communication channel. During the data transmission process, quantum encryption algorithms are used to ensure the security and integrity of the data.

[0037] In the data processing center, we use an adaptive time-varying learning rate optimization algorithm to process the received data. We process the data in segments through the sliding window technology, calculate the data change rate and fluctuation in each window, and dynamically adjust the learning rate parameters to improve the efficiency and accuracy of data processing. At the same time, we use dynamic gradient pruning technology to select and retain important gradient paths according to the gradient size, prune unimportant gradients, and reduce the amount of calculation.

[0038] In order to further improve the authenticity and diversity of data, we use the generative adversarial network model to simulate geographic data changes. By training the generative network and the discriminative network, simulated data similar to the actual data is generated, and the generated data is fused with the actual data. For data from different sensors, the Bayesian network fusion method is used to perform comprehensive processing based on the prior probability and conditional probability of the data source to achieve efficient fusion of multi-source data.

[0039] The processed and fused geographic data is processed in parallel through quantum state superposition optimization algorithm combined with quantum interference optimization and error correction technology to improve the stability and reliability of data processing. Finally, the processed and fused geographic data is updated to the geographic information system in real time, and the real-time updated geographic data is visualized. Through high-performance graphics rendering engine and virtual reality and augmented reality technology, intuitive three-dimensional geographic data display and interactive functions are provided.

[0040] To verify the effectiveness of this method, we The region was tested for a month, and the specific data are as follows: Data collection: The amount of data collected every day is , a total of about .

[0041] Data processing time: After adopting the adaptive time-varying learning rate optimization algorithm, the data processing time was reduced from 8 hours per day to 2 hours.

[0042] Data transmission security: After adopting the quantum encryption algorithm, no data leakage or tampering occurs during data transmission.

[0043] Data fusion accuracy: The generative adversarial network model and Bayesian network fusion method improved the data fusion accuracy by 15%.

[0044] Data update frequency: Through the quantum state superposition optimization algorithm, the data update frequency is increased from once per hour to once per minute.

[0045] Data visualization effect: Through and technology, users' understanding and application of geographic data have increased by 30%.

[0046] Our approach is In regional applications, the efficiency of data processing, the accuracy and security of fusion, the frequency of data updates and the visualization effect have been significantly improved, achieving the expected beneficial effects and verifying the effectiveness and reliability of the method in actual scenarios.

[0047] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A real-time updating method for geographic surveying and mapping data based on an adaptive algorithm, characterized in that: The following steps are involved: S1. Deploy a widely distributed sensor network to collect geographic data in real time; S2, transmitting geographic data to a data processing center; S3, using an adaptive time-varying learning rate optimization algorithm to dynamically adjust the learning rate parameters by monitoring the rate of change and fluctuation of geographic data; S4, using the generative adversarial network model to simulate the changes in geographic data and fuse the generated data with the actual data; S5. For geographic data from different sensors, a Bayesian network fusion method is used to perform comprehensive processing based on the prior probability and conditional probability of the data source; S6. Use quantum state superposition optimization algorithm combined with quantum interference optimization and error correction technology to process geographic data in parallel through quantum superposition state; S7, updating the processed and integrated geographic data to the geographic information system in real time; S8. Visualize the real-time updated geographic data.

2. The method for real-time updating of geographic surveying and mapping data based on an adaptive algorithm according to claim 1, characterized in that: The S1 comprises the following steps: S11, select multiple sensor installation locations in the target area, and the sensor network coverage is wide and evenly distributed; S12. Choose according to terrain, environment and surveying requirements. sensor, sensors, photogrammetric sensors, and meteorological sensors; S13, installing the sensor at the predetermined position, and the sensor is firmly fixed and operates normally; S14, configuring the working parameters of the sensor, including sampling frequency, data transmission frequency and data format; S15, start the sensor network, collect geographic data in real time, and transmit the data to the edge computing device through the wireless communication module; S16. Monitor the operating status of the sensor network, regularly calibrate and maintain sensors, and ensure the accuracy and continuity of data collection.

3. The method for real-time updating of geographic surveying and mapping data based on an adaptive algorithm according to claim 2, characterized in that: The S2 comprises the following steps: S21, deploy edge computing devices on sensor nodes to perform preliminary processing on real-time collected geographic data; S22. Use edge computing devices to pre-process data, including data cleaning, data filtering, and data compression.

4. The method for real-time updating of geographic surveying and mapping data based on an adaptive algorithm according to claim 3 is characterized in that: The S3 comprises the following steps: S31. Use sliding window technology to process geographic data in segments and set the size of the sliding window ,in, The size is determined according to the frequency of data collection and update requirements; S32. Calculate the geographic data change rate in each sliding window and fluctuations ,in: For the The standard deviation of the data in the sliding window; S33, set the initial learning rate and adjustment factor , through the formula: Dynamically adjust learning rate ,in For the The learning rate of the iteration, To avoid division by zero, use a very small constant; S34, use the adaptive time-varying learning rate optimization algorithm to iteratively process the geographic data. In each iteration, the learning rate parameter is updated according to the data change rate and fluctuation in the current sliding window. ; S35. In each iteration, calculate the gradient of data processing , combined with adaptive learning rate Update model parameters ; S36, using dynamic gradient pruning technology, in each iteration, select and retain important gradient paths according to the gradient size, prune unimportant gradients, and reduce the amount of calculation: ； in, For the parameters, is the gradient pruning threshold, is the gradient of data processing; S37. During the data processing, the learning rate adjustment effect is monitored in real time, and the adjustment strategy is further optimized based on the real-time monitoring data: ； in, is the adjustment factor, The final adjusted learning rate is applied to the processing and analysis of geographic data.

5. The method for real-time updating of geographic surveying and mapping data based on an adaptive algorithm according to claim 4, characterized in that: The S4 comprises the following steps: S41. Construct a generative adversarial network model, including a generative network and a discriminative network. The input of the generative network is a noise vector , the output is simulated geographic data , the input of the discriminant network is the actual geographic data and generate data , the output is the judgment result and ; S42. Initialize the parameters of the generation network and the discrimination network and , set the initial learning rate and , and the number of training rounds and batch size ; S43. For each training round , perform the following steps: S431, generate noise vector by sampling from noise distribution , and input the generated network to generate simulated geographic data ; S432. Randomly sample real data from actual geographic data distribution ; S433. Calculate the loss function of the discriminant network : ； in, represents the discriminant network, Indicates A sample of actual data, represents the generative network, Indicates A noise vector, Indicates the batch size; S434, use stochastic gradient descent method to update the parameters of the discriminant network : ； in, represents the parameters of the discriminant network, represents the learning rate, Represents the discriminant network loss function about The gradient of S435. Calculate the loss function of the generated network : ； in, represents the loss function of the generated network, Indicates A noise vector, Indicates the batch size; S436, use stochastic gradient descent method to update the parameters of the generated network : ； in, To generate the parameters of the network, To generate the network loss function about The gradient of S44. During the training process, data is generated by calculation and actual data The mean square error is: ； Among them, the mean square error is a measure of the difference between the generated data and the actual data. is the sample size, For the A sample of actual data, Generate the network generated simulated data samples, Indicates A noise vector; S45. After training is completed, use the generated data and actual data Fusion strategy, calculate the fusion data after weight optimization : S451, calculation and generation of data and actual data Statistical properties of , and variance , ; S452. Determine weight and , so that the fusion data The statistical properties of are close to those of the actual data: ； ； in, and are the mean and variance of the fused data respectively, satisfying and ; S453, by minimizing the following loss function Determining the optimal weights and : ； Among them, the mean , is the mean, , is the variance, and are the mean and variance of the fused data respectively; S454, use gradient descent method to optimize weights and : ； ； in, and is the weight of generated data and actual data, is the loss function for weight optimization, The learning rate optimized for the weights; S46. The fused geographic data Input into subsequent data processing and analysis process.

6. The method for real-time updating of geographic surveying and mapping data based on an adaptive algorithm according to claim 5, characterized in that: The S5 comprises the following steps: S51. Collect data from different sensors, including data, data, photogrammetric data, and meteorological data; S52, preprocess the data of each sensor and extract feature vectors ; S53. Establishing Bayesian network model , defines the prior probability of each data source and conditional probability, ,in Represents different data sources; S54. Calculate the dynamic prior probability of each data source , based on the weighted fusion of historical data and real-time data: ； in, is the weighting coefficient, is the prior probability of historical data, is the prior probability of real-time data; S55. Calculate conditional probability When , an adaptive parameter adjustment mechanism is introduced to dynamically adjust according to the correlation between data sources: ； ； in, For data source and The correlation coefficient between Data Source The standard deviation of For data source The standard deviation of S56. Comprehensively process data from different sensors and use enhanced Bayesian inference methods to calculate fused geographic data : ； in, is the fused geographic data. For data from different sensors; S57, introduce a dynamic adjustment mechanism to maximize the posterior probability , optimize the fused geographic data : ； in, The dynamic weight coefficient for each data source is adjusted according to the reliability and real-time performance of the data source; S58. The fused geographic data Input into subsequent data processing and analysis process.

7. The method for real-time updating of geographic surveying and mapping data based on an adaptive algorithm according to claim 6, characterized in that: The S6 comprises the following steps: S61. Quantum state initialization and encoding: Constructing the initial quantum state and encoding multi-source geographic data Dynamically encoded as quantum states : ； in, and According to geographic data characteristics and Dynamically adjusted amplitude coefficients satisfy the normalization condition: ； S62, Quantum state adaptive filtering and error correction: Combining quantum adaptive filtering and error correction mechanism: ； ； in, is the quantum state adaptive filtering operator, is the quantum error correction operator, is the filtering parameter, is the learning rate, is the loss function, and are the weight and adjustment value of the feedback error respectively; S63. Multi-source data quantum fusion: Using the superposition characteristics of quantum states, geographic data from different sources are integrated into one quantum state: ； in, is a quantum method operator for multi-source data fusion, is the corresponding data fusion parameter; S64, Quantum Phase Change Optimization: Introducing quantum phase change detection and optimization to identify key changes in geographic data and optimize processing: ； ； in, Optimizing operators for quantum phase transitions, To optimize the parameters, is the phase change detection parameter, Optimize the step size for phase transition, To optimize the objective function, and , are the weight and adjustment value of the optimized feedback error respectively; S65, Adaptive feedback control: Use the adaptive feedback control mechanism to monitor and adjust processing parameters in real time and optimize the data processing process: ； in, , is the learning rate, is the feedback control function, and are the weight and adjustment value of the feedback error respectively; S66. Quantum state measurement and result generation: Perform quantum measurement on the optimized quantum state to obtain optimized geographic data: ； in It is the measurement operator used to convert quantum states into classical data.

8. The method for real-time updating of geographic surveying and mapping data based on an adaptive algorithm according to claim 7, characterized in that: The S7 comprises the following steps: S71, pre-processing the processed and fused geographic data, and using an adaptive noise filtering algorithm to eliminate noise and outliers; S72, compressing the preprocessed geographic data, using a dynamic compression ratio adjustment algorithm to dynamically adjust the compression ratio according to data characteristics; S73, encrypting the compressed geographic data; S74, transmitting the encrypted geographic data to the geographic information system through a secure communication channel; S75, decrypting the received geographic data at the geographic information system end, and restoring the original state of the data using a quantum decryption algorithm; S76, decompressing the decrypted geographic data and restoring complete information of the data using an adaptive decompression algorithm; S77. Update the decompressed geographic data to the geographic information system in real time, and use an adaptive update algorithm to dynamically adjust the update strategy according to changes in real-time data.

9. The method for real-time updating of geographic surveying and mapping data based on an adaptive algorithm according to claim 8, characterized in that: The S8 comprises the following steps: S81. Convert real-time updated geographic data into a format suitable for visual display, using data normalization and standardization; S82, performing three-dimensional modeling on the converted geographic data, using a grid-based modeling technology to generate a three-dimensional geographic model; S83, performing texture mapping on the three-dimensional geographic model; S84. Interactive design of textured three-dimensional geographic models using virtual reality and augmented reality technologies; S85, performing real-time rendering of the interactive three-dimensional geographic model using a graphics rendering engine; S86: Visually display the real-time rendered geographic image on the user terminal to achieve real-time visual display of geographic data.

Images