Electronic map making method based on basic geographic information data

Abstract

The invention relates to the technical field of electronic map making, in particular to an electronic map making method based on basic geographic information data, which comprises the following steps: selecting geographic information data, combining existing map data with regional previous geographic event records, collecting corresponding time and position parameters, and synthesizing into basic geographic time sequence data. According to the method, basic geographic time sequence data is formed by integrating historical geographic event records and existing map data, the long-term trend of city expansion and road use can be effectively captured, future geographic land use changes can be predicted by analyzing the data through the recurrent neural network, a prospective basis is provided for map making, and the method is suitable for popularization and application. The hidden Markov model is used for further refining the state transition and observation probability, complex geographic state changes can be simulated, multiple regression is executed after traffic and climate data are integrated, it is ensured that the output map information reflects the latest geographic state, and the accuracy and response speed of the map are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic map making, and in particular to an electronic map making method based on basic geographic information data. Background Art

[0002] The field of electronic mapping technology involves the use of computers and geographic information systems (GIS) to create, edit, and update maps. This field combines multiple technologies, including big data processing, image rendering, location data analysis, and user interface design. Electronic maps not only provide traditional geographic location information but also enable real-time updates of traffic conditions, weather changes, and other environmental data, greatly enhancing the map's practicality and interactivity. This technology is widely used in navigation systems, urban planning, emergency response, and commercial geographic analysis.

[0003] The "Electronic Mapping Method Using Basic Geographic Information Data" refers to the technical process of generating and updating electronic maps using basic geographic information data. This method typically involves collecting geographic coordinate data, terrain, building outlines, road networks, and other information and converting it into digital maps. This theme aims to provide accurate map information to assist users with location positioning, route planning, and geographic analysis. It is suitable for smartphone applications, in-vehicle navigation systems, and web map services.

[0004] Existing technologies for real-time map data updates often fail to reflect the latest urban and traffic conditions due to a lack of effective mechanisms for leveraging historical geographic events. This results in maps that are not current or accurate. Manual updates of map data are limited in processing speed and accuracy, and are prone to errors during the update process. These issues can lead to users relying on maps to make decisions encountering incomplete information, such as incorrect traffic routes or outdated urban layout information, impacting travel efficiency and planning outcomes. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an electronic map making method based on basic geographic information data.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a method for making an electronic map based on basic geographic information data, comprising the following steps:

[0007] S1: Select geographic information data, combine existing map data with regional historical geographic event records, collect corresponding time and location parameters, and synthesize them into basic geographic time series data;

[0008] S2: Based on the basic geographic time series data, set the parameters of the recurrent neural network, analyze the urban expansion and road use data in the time series, identify the characteristics of urban land use changes, collect road use frequency information, evaluate traffic flow changes, construct a data input vector, perform recurrent operations, and obtain a prediction trend model;

[0009] S3: Using the forecast trend model to generate input conditions of a hidden Markov model, setting a state transition and observation probability matrix, simulating geographic state changes, optimizing probability parameters through multiple iterations, and outputting geographic state probability analysis results;

[0010] S4: integrating the geographic state probability analysis results with traffic flow and climate change information, performing multiple regression analysis, repeatedly adjusting the data until the data reaches a stable state, and generating real-time data fusion analysis results;

[0011] S5: According to the real-time data fusion analysis results, automatically adjust map data parameters, including road width and building status, update the map database, and record map automatic correction data.

[0012] The basic geographic time series data includes map data, geographic event records, time parameters, and location parameters. The prediction trend model specifically includes urban land use change characteristics, road use frequency, and traffic flow changes. The geographic state probability analysis results include state transition probability, observation probability, and geographic state changes. The real-time data fusion analysis results specifically refer to traffic flow data, climate change information, and multiple regression analysis results. The map automatic correction data includes road width parameters, building status updates, and map database records.

[0013] As a further solution of the present invention, the steps for obtaining the basic geographic time series data are specifically as follows:

[0014] S111: Integrate regional geographic event records and map data, filter the location and occurrence time of each event, classify them according to the geographic coordinate system, and generate a geographic event classification set;

[0015] S112: Serializing the geographic event classification set in chronological order, time-stamping each event, and generating a time-stamped geographic event sequence;

[0016] S113: Adjust the time interval of the time-stamped geographic event sequence by applying the weighted average formula:

[0017]

[0018] Generate basic geographic time series data;

[0019] Among them, S georepresents the basic geographic time series data, N represents the total number of events in the sequence, and α i represents the time weight of the i-th event, which is used to adjust the criticality of the event in the sequence, β i represents the attenuation factor, Δt i Indicates the time difference since the last event, Loc i Indicates the location coordinates.

[0020] As a further solution of the present invention, the step of identifying the characteristics of urban land change is specifically as follows:

[0021] S211: Based on the basic geographic time series data, screening events associated with urban expansion, including land use changes and new construction areas, marking the geographic and temporal characteristics of multiple events, and generating a comprehensive preliminary urban land use change record;

[0022] S212: extracting time stamps and geographic locations from the comprehensive urban land preliminary change records, determining the occurrence pattern and frequency of the changes, and obtaining urban land change pattern data;

[0023] S213: Analyze and calculate the urban land change pattern data using the formula:

[0024]

[0025] Using geographical and temporal variables, we calculated the land use change rate of each region and obtained the characteristics of urban land use change.

[0026] Among them, S change represents the characteristics of urban land use change, M represents the total number of analyzed areas, ΔA i represents the area change of the i-th region, ΔT i represents the time span over which the change occurs, γ i is the weight coefficient of the ith region, which is adjusted according to the development criticality or environmental sensitivity of the region.

[0027] As a further solution of the present invention, the steps of obtaining the prediction trend model are specifically as follows:

[0028] S221: extracting key variables including the change rate and regional expansion index from the urban land change characteristic data, integrating the data to construct an input vector, and generating preliminary input data for a prediction model;

[0029] S222: Based on the preliminary input data of the prediction model, setting the associated parameters of the recurrent neural network, including the learning rate and the hidden layer structure, to match the complexity of the urban development trend, and obtaining the configured network parameters;

[0030] S223: Execute a loop operation to process the configured network parameters using the formula:

[0031]

[0032] Use nonlinear activation functions for pattern recognition to obtain a predictive trend model;

[0033] Among them, w k represents the weight of the kth input, reflecting the influence of the input in the prediction model, x k represents the kth data point in the input vector, and b is the bias term used to adjust the model output.

[0034] As a further solution of the present invention, the steps for obtaining the geographic state probability analysis result are specifically as follows:

[0035] S311: extracting key performance indicators from the data output by the forecast trend model, including the change trend and change rate of the geographical area, integrating the data to construct preliminary input conditions of the hidden Markov model, and generating forecast input data for state changes;

[0036] S312: According to the predicted input data of the state change, the state transition probability and observation probability matrix of the hidden Markov model are set, and corresponding probability values are obtained by calculation to generate a configured probability matrix;

[0037] S313: Based on the configured probability matrix, iteratively optimize the state transition and observation probability matrices using the probability optimization formula:

[0038]

[0039] Adjust the probability parameters of each state, simulate the changes in geographical state, and generate geographical state probability analysis results;

[0040] Among them, λ n Represents the critical adjustment coefficient of the nth state, p n Represents the initial probability value of the state before adjustment, which is the original state probability calculated by the model based on the observed data, and N represents the total number of states in the model.

[0041] As a further solution of the present invention, the steps for obtaining the real-time data fusion analysis results are specifically as follows:

[0042] S411: Integrate the geographic state probability analysis results with the traffic flow data, incorporate climate change information, create a multidimensional data framework through data alignment and format unification, prepare normalized input vectors for multiple regression analysis, and generate a primary data framework for comprehensive analysis;

[0043] S412: Based on the primary data framework of the comprehensive analysis, perform a multiple regression analysis to determine the relevance and prediction strength of the influencing factors, repeatedly adjust the model parameters until the optimal fit is obtained, and obtain the adjusted regression model parameters;

[0044] S413: Calculate the contribution of each variable based on the adjusted regression model parameters, using the stability test formula:

[0045]

[0046] After the data reaches a stable state, the iteration is stopped and real-time data fusion analysis results are generated;

[0047] Among them, c i Represents the adjustment coefficient of the i-th variable, which is used to adjust the influence weight of the variable in the model, V i Represents the variable value, which is the numerical value extracted from the data set and used as the actual input data in the regression analysis. i It is the nonlinear adjustment index of the variable, which is used to increase the matching of the model to the nonlinear characteristics of the data. ∈ is a very small constant.

[0048] As a further solution of the present invention, the step of recording the automatic map correction number is specifically as follows:

[0049] S511: Extracting key indicators that affect map parameters, including changes in road usage frequency and building conditions, based on the real-time data fusion analysis results, and generating an initial data set for map parameter adjustment;

[0050] S512: Automatically updating the road width and building status in the map database using the initial data set for map parameter adjustment to obtain an updated map parameter configuration;

[0051] S513: Execute automatic correction according to the updated map parameter configuration, record the data and time of each parameter change, and use the formula:

[0052]

[0053] Generate map automatic correction data;

[0054] Among them, α i Represents the adjustment coefficient of the road width parameter, which is the weight of dynamically adjusting the road width according to the road usage frequency data. i Road usage data refers to the road traffic or usage frequency collected in real time, β i is the adjustment coefficient of building status parameters, B i Represents building status data, including building maintenance, damage level, or update frequency, γ iis the time sensitivity adjustment coefficient, which is used to adjust the influence of time variables, T i Indicates a time period, reflecting the time that has passed since the last update.

[0055] Compared with the prior art, the advantages and positive effects of the present invention are:

[0056] This invention integrates historical geographic event records with existing map data to form basic geographic time series data, effectively capturing long-term trends in urban expansion and road use. Analyzing this data using a recurrent neural network can predict future changes in geographic land use, providing a forward-looking foundation for map production. Hidden Markov models are used to further refine state transitions and observation probabilities, enabling simulation of complex geographic state changes. After integrating traffic and climate data, multivariate regression is performed to ensure that the output map information reflects the latest geographic conditions, improving map accuracy and responsiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 It is a schematic diagram of the main steps of the present invention;

[0058] Figure 2 This is a flow chart of the steps for obtaining basic geographic time series data of the present invention;

[0059] Figure 3 A flow chart showing the steps of identifying the characteristics of urban land use changes in the present invention;

[0060] Figure 4 Flowchart of the steps for obtaining the prediction trend model of the present invention;

[0061] Figure 5 Flowchart of the steps for obtaining the geographic status probability analysis results of the present invention;

[0062] Figure 6 Flowchart of the steps for obtaining the real-time data fusion analysis results of the present invention;

[0063] Figure 7 The present invention is a flowchart of the steps of recording automatic map correction numbers. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0065] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0066] Example 1

[0067] See also Figure 1 The present invention provides a technical solution: an electronic map making method based on basic geographic information data, comprising the following steps:

[0068] S1: Select geographic information data, combine existing map data with regional historical geographic event records, collect corresponding time and location parameters, and synthesize them into basic geographic time series data;

[0069] S2: Based on basic geographic time series data, set the parameters of the recurrent neural network, analyze the urban expansion and road use data in the time series, identify the characteristics of urban land use changes, collect road use frequency information, evaluate traffic flow changes, construct data input vectors, perform recurrent operations, and obtain a predictive trend model;

[0070] S3: Use the forecast trend model to generate the input conditions of the hidden Markov model, set the state transition and observation probability matrix, simulate the geographical state changes, optimize the probability parameters through multiple iterations, and output the geographical state probability analysis results;

[0071] S4: Integrate the geographic state probability analysis results with traffic flow and climate change information, perform multiple regression analysis, repeatedly adjust the data until it reaches a stable state, and generate real-time data fusion analysis results;

[0072] S5: Based on the real-time data fusion analysis results, automatically adjust the map data parameters, including road width, building status, update the map database, and record the map automatic correction data.

[0073] Basic geographic time series data include map data, geographic event records, time parameters, and location parameters. The prediction trend model specifically includes the characteristics of urban land use changes, road use frequency, and traffic flow changes. The geographic state probability analysis results include state transition probability, observation probability, and geographic state changes. The real-time data fusion analysis results specifically refer to traffic flow data, climate change information, and multiple regression analysis results. Map automatic correction data includes road width parameters, building status updates, and map database records.

[0074] See also Figure 2 ,The specific steps for obtaining basic geographic time series data are:

[0075] S111: Integrate regional geographic event records and map data, filter the location and occurrence time of each event, classify them according to the geographic coordinate system, and generate a geographic event classification set;

[0076] By integrating regional geographic event records with map data, screening the location and time of occurrence of each event, and classifying and processing them according to the geographic coordinate system, this classification processing involves the application of the geographic coordinate system. By systematically corresponding geographic events with map data, the accuracy and practicality of the data are ensured. On the basis of event classification, the professionalism and target of data processing are strengthened. The process of classification according to the geographic coordinate system involves not only basic data collection, but also strict screening of data validity and accuracy, ensuring the authenticity and reliability of the data in the classification set. The generated geographic event classification set provides a solid foundation for the next step of time series processing.

[0077] S112: Serializing the geographic event classification set in chronological order, time-stamping each event, and generating a time-stamped geographic event sequence;

[0078] Time serialization of the geographic event classification set involves the operation of time-stamping each event to ensure the temporal continuity of the event. In this process, event time verification and serialization marking are performed. By reviewing and sorting the timestamps of each geographic event, the accuracy and logic of the sequence data on the time axis are guaranteed. The time-stamping process refers not only to the order of time but also to the time intervals between data points to ensure the consistency and comparability of the time series. The generated time-stamped geographic event sequence provides a standardized and standardized time frame for data analysis.

[0079] S113: Adjust the time interval of the time-stamped geographic event sequence and apply the weighted average formula:

[0080]

[0081] Generate basic geographic time series data;

[0082] Among them, S geo represents the basic geographic time series data, N represents the total number of events in the sequence, and α i represents the time weight of the i-th event, which is used to adjust the criticality of the event in the sequence, β i represents the attenuation factor, Δt i Indicates the time difference since the last event, Loc i Indicates the location coordinates.

[0083] formula:

[0084]

[0085] The benefit of the formula is that by combining time decay and location weights, it can effectively adjust the time intervals and geographic precision in time series data. Such weight adjustments reflect the criticality of the time and location of geographic events to the overall data analysis, optimizing the data expression of time series.

[0086] Detailed explanation of the formula and the process of formula calculation and derivation:

[0087] Set the parameter values as follows: N = 100, α i =0.5 sets all events as critical, β i =0.05 represents the time decay rate, Δt i Let Δt be the time difference between event i and the previous event, in hours. i =2 hours, Loc i is the coordinate value of the event location, set to 10, and the calculation process is as follows:

[0088] 1. Evaluate the expression within each term:

[0089] 2. Multiply the location coordinates by the result of step 1: 0.4524 × 10 = 4.524

[0090] 3. Add up all the event results and divide by the total number of events:

[0091] The results show that the overall eigenvalue of the geographical event time series is 4.524, which comprehensively reflects the time impact and location criticality of the event. i and β i , the effects of differentiated time decay and location weights can be analyzed iteratively.

[0092] See also Figure 3 ,The steps to identify the characteristics of urban land use changes are as follows:

[0093] S211: Based on basic geographic time series data, screen events associated with urban expansion, including land use changes and new construction areas, mark the geographic and temporal characteristics of multiple events, and generate comprehensive preliminary urban land use change records;

[0094] Based on basic geographic time series data, urban expansion-related events, including land use changes and new construction areas, are extracted and preliminarily classified and labeled to determine the geographical and temporal characteristics of each event. By combining geographic information system (GIS) technology and time series analysis methods, preliminary urban land use change records are generated. These records reflect the dynamic changes of urban land at different time points, including the transformation of land cover types and the expansion of new development areas. By analyzing the data, the main trends and expansion patterns of urban development are identified, providing a basis for urban planning and land management.

[0095] S212: extracting time stamps and geographic locations from the comprehensive urban land preliminary change records, determining the occurrence pattern and frequency of the changes, and obtaining urban land change pattern data;

[0096] Key information is extracted from the preliminary change records of urban land use, and the pattern and frequency of urban land use changes are determined through time series analysis. The key is to analyze the speed and trend of urban expansion by comparing data at different time points. This process involves the processing and analysis of time series data, and the use of various statistical tools to determine the change pattern, including calculating the change frequency and trend line analysis. This information helps identify key urban expansion areas and rates, and provides a scientific basis for urban planning and related policy formulation.

[0097] S213: Analyze and calculate the urban land use change pattern data using the formula:

[0098]

[0099] Using geographical and temporal variables, we calculated the land use change rate of each region and obtained the characteristics of urban land use change.

[0100] Among them, S change represents the characteristics of urban land use change, M represents the total number of analyzed areas, ΔA i represents the area change of the i-th region, ΔT i represents the time span over which the change occurs, γ i is the weight coefficient of the ith region, which is adjusted according to the development criticality or environmental sensitivity of the region.

[0101] formula:

[0102]

[0103] The benefit of the formula is that it provides a method to quantify the rate of change of urban land use. By combining the area change of each region with the time span and multiplying it by an adjustment coefficient, the characteristics of urban land use change can be calculated, which is of key significance for urban planning and land use decision-making.

[0104] Detailed explanation of the formula and the process of formula calculation and derivation:

[0105] There are three regions, and the area change and time span data of each region are as follows:

[0106] Area 1: ΔA1 = 2 km 2 , ΔT1=1year,γ1=1.5

[0107] Area 2: ΔA2 = 3 km 2 , ΔT2=2years,γ2=1.2

[0108] Area 3: ΔA3 = 1.5 km 2 , ΔT3=1.5years, γ3=1.3

[0109] Calculate the land use change rate of multiple regions:

[0110] Region 1:

[0111]

[0112] Region 2:

[0113]

[0114] Region 3:

[0115]

[0116] Substitute the formula to calculate the overall land use change characteristics:

[0117]

[0118] The results show that the average rate of change in urban land use is 2.033 square kilometers per year, reflecting the rapidity of urban expansion. This value can be used to evaluate the effectiveness of urban land use policies and areas that need to be focused on.

[0119] See also Figure 4 , the specific steps for obtaining the forecast trend model are:

[0120] S221: Extract key variables including change rate and regional expansion index from urban land change characteristic data, integrate the data to construct input vectors, and generate preliminary input data for the prediction model;

[0121] Key variables including the rate of change and regional expansion index are extracted from the urban land use change characteristic data, and the data are integrated to construct input vectors. These data points include land use changes in differentiated regions and time. They are processed through geographic information systems (GIS) and time series analysis tools to ensure the accuracy and applicability of the data. The generated input vectors will directly affect the predictive ability of the model and are the basis for establishing an effective prediction model.

[0122] S222: Based on the preliminary input data of the prediction model, set the associated parameters of the recurrent neural network, including the learning rate and hidden layer structure, to match the complexity of the urban development trend, and obtain the configured network parameters;

[0123] Based on preliminary input data, the associated parameters of the recurrent neural network, including the learning rate and hidden layer structure, are set to match the complexity of urban development trends. The parameter setting is based on the trend of urban development data and the needs of pattern recognition. Existing urban development cases are used for simulation to determine the optimal network structure and parameters. This process involves batch data testing and verification to ensure that the network configuration can effectively process the input data and improve the model's prediction accuracy and response speed.

[0124] S223: Execute loop operation to process the configured network parameters using the formula:

[0125]

[0126] Use nonlinear activation functions for pattern recognition to obtain a predictive trend model;

[0127] Among them, w k represents the weight of the kth input, reflecting the influence of the input in the prediction model, x k represents the kth data point in the input vector, and b is the bias term used to adjust the model output.

[0128] formula:

[0129]

[0130] The benefit of this formula is that by introducing the absolute value of the product of the weight and the input data and then taking the square root, the model's sensitivity to input changes can be nonlinearly enhanced. This can improve the model's ability to respond to abnormal data, thereby improving the accuracy of the prediction.

[0131] Detailed explanation of the formula and the process of formula calculation and derivation:

[0132] There are three data points, w = [0.5, 0.3, 0.2], x = [20, 30, 50] and bias b = 0.1.

[0133] 1. Calculate wk ·x k :

[0134] [0.5×20, 0.3×30, 0.2×50]=[10, 9, 10]

[0135] 2. Take the absolute value and sum it:

[0136] |10|+|9|+|10|=29

[0137] 3. Take the square root:

[0138]

[0139] 4. Apply bias and formula:

[0140]

[0141] The results show that under given weights and input values, the forecast trend model outputs an adjusted result of approximately 0.286, which reflects the model's sensitivity to changes in input data and improves the matching of data through nonlinear processing.

[0142] See also Figure 5 , the specific steps for obtaining the results of geographic state probability analysis are:

[0143] S311: Extract key performance indicators from the output data of the forecast trend model, including the change trend and change rate of the geographical area, integrate the data to construct the preliminary input conditions of the hidden Markov model, and generate the forecast input data of the state change;

[0144] When generating input data, key performance indicators were derived through a geographic information system (GIS) and time series analysis. Python's Pandas library was used to process time series data to identify trends and rates of change. This data was extracted from geographic monitoring data from the past decade. Cluster analysis was performed on the annual change data for each geographic region, using the K-means clustering algorithm to identify key patterns of change. This step ensured that the input data for the hidden Markov model was both accurate and representative, allowing simulations of geographic state changes over future time periods.

[0145] S312: According to the predicted input data of the state change, the state transition probability and observation probability matrix of the hidden Markov model are set, the corresponding probability values are obtained by calculation, and the configured probability matrix is generated;

[0146] The process of setting up the state transition probability and observation probability matrix first requires analyzing and identifying the predicted and observed outcomes for multiple states from the input data. This process involves mathematical calculations, using Bayesian statistics to update and refine the probability estimates. Furthermore, the observation probabilities are calculated based on direct observational records of geographic state changes, acquired through remote sensing techniques, including satellite imagery and data from ground-based monitoring stations. The transition probability for each state is derived from a statistical analysis of previous data, leveraging past state sequences to predict future state changes.

[0147] S313: Based on the configured probability matrix, iteratively optimize the state transition and observation probability matrices using the probability optimization formula:

[0148]

[0149] Adjust the probability parameters of each state, simulate the changes in geographical state, and generate geographical state probability analysis results;

[0150] Among them, λ n Represents the critical adjustment coefficient of the nth state, p n Represents the initial probability value of the state before adjustment, which is the original state probability calculated by the model based on the observed data. N represents the total number of states in the model.

[0151] formula:

[0152]

[0153] The benefit of the formula is that it integrates the probability values of differentiated states through weighted averaging and increases the certainty of the prediction through the square operation, making the model more sensitive to changes in states with higher probability.

[0154] Detailed explanation of the formula and the process of formula calculation and derivation:

[0155] In the formula, the probability p of each state is n It is calculated by monitoring the frequency of changes in geographical states. If a geographical state has appeared 100 times during the past observation period, the probability of the state is 100 divided by the total number of observations. n It is based on the criticality score of the geographical state, which is obtained through expert evaluation. If a geographical state affects an ecologically protected area, the criticality score will be higher than that of an ordinary area. In a model with five states, the number of observations of each state is 10, 20, 30, 25, and 15, and the criticality scores are set to 1.2, 1.0, 0.8, 1.5, and 1.3 respectively. First, calculate the numerator before weighted average:

[0156]

[0157] The denominator is:

[0158]

[0159] The calculation formula is:

[0160]

[0161] The results show that the state change predictions of the overall model are more biased towards states with higher criticality, which in practical applications means that the model will pay more attention to changes in ecological protection areas or other key geographical areas.

[0162] See also Figure 6 ,The specific steps for obtaining the real-time data fusion analysis results are as follows:

[0163] S411: Integrate geographic state probability analysis results with traffic flow data, incorporate climate change information, create a multidimensional data framework through data alignment and format unification, prepare normalized input vectors for multiple regression analysis, and generate a primary data framework for comprehensive analysis;

[0164] In the process of integrating the results of geographic state probability analysis with traffic flow data, it is first necessary to collect and organize existing data, including geographic state change probability data and real-time records of traffic flow. These data come from geographic information systems and traffic monitoring systems. The accuracy and real-time nature of the data are crucial to the analysis results. Next, through data cleaning and data normalization, the consistency and comparability of the data format are ensured. Climate change information also needs to be collected synchronously, including climate indicators such as temperature, precipitation, and wind speed. The indicators are obtained through real-time monitoring of meteorological stations. During the data processing process, SQL and Python are used to query, filter, and preprocess the data to provide normalized input vectors for multivariate regression analysis. In this way, the processed data can not only reflect the status of a single variable, but also show the dynamic relationship and interaction between differentiated variables, generating a primary data framework for comprehensive analysis.

[0165] S412: Based on the primary data framework of comprehensive analysis, perform multiple regression analysis to determine the relevance and predictive strength of influencing factors, repeatedly adjust model parameters until the optimal fit is achieved, and obtain the adjusted regression model parameters;

[0166] In the process of performing multiple regression analysis, you first need to choose to use R or MATLAB, which provides powerful data processing and analysis functions and can effectively process batch data sets. Analysts need to set model parameters according to the research objectives, including independent variables and dependent variables. These variables come from the data framework organized in the previous step. Before using these software for regression analysis, the data needs to be standardized to eliminate dimensional effects and potential correlations between variables. Then, the regression analysis is performed, and the model parameters are repeatedly adjusted during the process. The model fit and prediction accuracy are evaluated through residual analysis and multicollinearity tests to ensure that the coefficient of each factor reflects its true impact on the results. In this way, it is possible to determine how multiple factors interact with each other and their impact on the prediction model, and obtain the adjusted regression model parameters.

[0167] S413: Calculate the contribution of each variable based on the adjusted regression model parameters, using the stability test formula:

[0168]

[0169] After the data reaches a stable state, the iteration is stopped and real-time data fusion analysis results are generated;

[0170] Among them, c i Represents the adjustment coefficient of the i-th variable, which is used to adjust the influence weight of the variable in the model, V i Represents the variable value, which is the numerical value extracted from the data set and used as the actual input data in the regression analysis. i It is the nonlinear adjustment index of the variable, which is used to increase the matching of the model to the nonlinear characteristics of the data. ∈ is a very small constant.

[0171] formula:

[0172]

[0173] The benefit of the formula is that it enhances the robustness of the model to data outliers by introducing nonlinear adjustment exponents and smoothing terms of variables, and optimizes the response of the model to the sensitivity of differentiated data by adjusting the coefficients, making the model more flexible in matching the changing trends of differentiated data.

[0174] Detailed explanation of the formula and the process of formula calculation and derivation:

[0175] The values of the three variables are set to V1 = 100, V2 = 150, and V3 = 200, the corresponding adjustment coefficients are c1 = 0.5, c2 = 0.3, and c3 = 0.2, the nonlinear adjustment exponents are d1 = 2, d2 = 3, and d3 = 1, and the smoothing term epsilon is 0.01. The calculation process is as follows:

[0176] Apply the formula to each variable to calculate the adjusted variable value:

[0177]

[0178] Add up all adjusted variable values to get the result:

[0179] R stable =500+827.24+2.83≈1330.07

[0180] The results show that the model can effectively process data of different scales and sensitivities and provide stable and reliable prediction results, which is particularly critical for real-time data analysis and can assist decision makers in analyzing and responding to environmental changes.

[0181] See also Figure 7 , the steps for recording the number of automatic map corrections are as follows:

[0182] S511: Based on the results of real-time data fusion analysis, key indicators that affect map parameters are extracted, including changes in road usage frequency and building conditions, to generate an initial data set for map parameter adjustment;

[0183] Based on the results of real-time data fusion analysis, the dynamic changes of urban expansion and environmental factors are integrated, and map data parameters are adjusted, including road width adjustments and building status updates. Road width parameters are optimized according to traffic flow data and regional development speed, and building data are updated in real time using GIS technology. These processes include obtaining current road and building status data from the geographic information system, combining it with real-time traffic information provided by the traffic management system, adjusting data parameters according to urban planning and development needs, iteratively analyzing data influencing factors, including peak traffic flow, building age and maintenance status, and using analysis results to determine data update priorities and adjustment strategies. The map database is automatically updated systematically, and information on each data adjustment is recorded to track data changes and data maintenance in future time periods.

[0184] S512: Automatically updating the road width and building status in the map database using the initial data set for map parameter adjustment to obtain an updated map parameter configuration;

[0185] The results of real-time data fusion analysis not only provide insights into urban expansion and environmental changes, but also make map data updates more accurate and timely. By analyzing the frequency of road use and building change records, map data parameters are automatically updated to ensure the practicality and accuracy of map services. The update process includes using the fused data to adjust the road width and building status in the map to reflect actual usage and physical status. The technologies involved in this step include data mining and machine learning algorithms, which are used to predict the future status of roads and buildings, ensuring the real-time and accuracy of map data. At the same time, each automatic correction data is recorded to support subsequent data analysis and urban planning.

[0186] S513: Execute automatic correction based on the updated map parameter configuration, record the data and time of each parameter change, and use the formula:

[0187]

[0188] Generate map automatic correction data;

[0189] Among them, α i Represents the adjustment coefficient of the road width parameter, which is the weight of dynamically adjusting the road width according to the road usage frequency data. i Road usage data refers to the road traffic or usage frequency collected in real time, β i is the adjustment coefficient of building status parameters, B i Represents building status data, including building maintenance, damage level, or update frequency, γ i is the time sensitivity adjustment coefficient, which is used to adjust the influence of time variables, T i Indicates a time period, reflecting the time that has passed since the last update.

[0190] formula:

[0191]

[0192] The formula is beneficial because it combines multiple factors to dynamically adjust the map data, including the frequency of road use (D i ) and building status (B i ), which are extracted from real-time data and weighted by the weight coefficient α i and β i Make matching adjustments to match the actual needs of urban development.

[0193] Detailed explanation of the formula and the process of formula calculation and derivation:

[0194] Assume that there are 3 key roads and 2 key buildings in a city that need to update their status, the road usage frequencies are 1000, 2000, and 1500 vehicles / hour, the building status scores are 80% and 70% (representing maintenance status), the weight coefficients are 0.5 and 0.3, the time sensitivity adjustment coefficient is 0.1, and the time period is 12 hours.

[0195]

[0196] The results show that by applying this formula, the automatic correction of map data can comprehensively refer to the influence of multiple factors, make dynamic adjustments to the data, and thus make the map service closer to the dynamic changes of the actual city.

[0197] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. An electronic map making method based on basic geographic information data, characterized in that: The following steps are involved: Select geographic information data, combine existing map data with records of past regional geographic events, collect corresponding time and location parameters, and synthesize them into basic geographic time series data; Based on the basic geographic time series data, recurrent neural network parameters are set, urban expansion and road use data in the time series are analyzed, characteristics of urban land use changes are identified, road use frequency information is collected, traffic flow changes are evaluated, a data input vector is constructed, and a recurrent operation is performed to obtain a prediction trend model; The forecast trend model is used to generate input conditions of a hidden Markov model, a state transition and observation probability matrix is set, geographic state changes are simulated, probability parameters are optimized through multiple iterations, and geographic state probability analysis results are output; Integrate the geographic state probability analysis results with traffic flow and climate change information, perform multiple regression analysis, repeatedly adjust the data until it reaches a stable state, and generate real-time data fusion analysis results; According to the real-time data fusion analysis results, map data parameters are automatically adjusted, including road width and building status, the map database is updated, and map automatic correction data is recorded.

2. The electronic map making method based on basic geographic information data according to claim 1, characterized in that: The basic geographic time series data includes map data, geographic event records, time parameters, and location parameters. The prediction trend model specifically includes urban land use change characteristics, road use frequency, and traffic flow changes. The geographic state probability analysis results include state transition probability, observation probability, and geographic state changes. The real-time data fusion analysis results specifically refer to traffic flow data, climate change information, and multiple regression analysis results. The map automatic correction data includes road width parameters, building status updates, and map database records.

3. The electronic map making method based on basic geographic information data according to claim 2, characterized in that: The steps for obtaining the basic geographic time series data are specifically as follows: Integrate regional geographic event records and map data, filter the location and time of each event, classify them by geographic coordinate system, and generate a geographic event classification set; Serializing the geographic event classification set in chronological order, time-stamping each event, and generating a time-stamped geographic event sequence; The time intervals of the time-stamped geographic event sequence are adjusted and the weighted average formula is applied: Generate basic geographic time series data; Among them, S geo represents the basic geographic time series data, N represents the total number of events in the sequence, and α i represents the time weight of the i-th event, which is used to adjust the criticality of the event in the sequence, β i represents the attenuation factor, Δt i Indicates the time difference since the last event, Loc i Indicates the location coordinates.

4. The electronic map making method based on basic geographic information data according to claim 3, characterized in that: The steps of identifying the characteristics of urban land use changes are specifically as follows: Based on the basic geographic time series data, screening events associated with urban expansion, including land use changes and new construction areas, marking the geographic and temporal characteristics of multiple events, and generating a comprehensive preliminary record of urban land use changes; Extracting time stamps and geographic locations from the comprehensive urban land preliminary change records, determining the occurrence pattern and frequency of the changes, and obtaining urban land change pattern data; The urban land change pattern data is analyzed and calculated using the formula: Using geographical and temporal variables, we calculated the land use change rate of each region and obtained the characteristics of urban land use change. Among them, S change represents the characteristics of urban land use change, M represents the total number of analyzed areas, ΔA i represents the area change of the i-th region, ΔT i represents the time span over which the change occurs, γ i is the weight coefficient of the ith region, which is adjusted according to the development criticality or environmental sensitivity of the region.

5. The electronic map making method based on basic geographic information data according to claim 4, characterized in that: The steps for obtaining the prediction trend model are specifically as follows: Extracting key variables including the change rate and regional expansion index from the urban land change characteristic data, integrating the data to construct an input vector, and generating preliminary input data for a prediction model; Based on the preliminary input data of the prediction model, setting the associated parameters of the recurrent neural network, including the learning rate and the hidden layer structure, to match the complexity of the urban development trend, and obtaining the configured network parameters; Perform a loop operation to process the configured network parameters using the formula: Use nonlinear activation functions for pattern recognition to obtain a predictive trend model; Among them, w k represents the weight of the kth input, reflecting the influence of the input in the prediction model, x k represents the kth data point in the input vector, and b is the bias term used to adjust the model output.

6. The electronic map making method based on basic geographic information data according to claim 5, characterized in that: The steps for obtaining the geographic state probability analysis result are specifically as follows: Extracting key performance indicators from the data output by the forecast trend model, including the trend and rate of change of the geographical area, integrating the data to construct preliminary input conditions for the hidden Markov model, and generating forecast input data for state changes; According to the predicted input data of the state change, the state transition probability and observation probability matrix of the hidden Markov model are set, the corresponding probability values are obtained by calculation, and the configured probability matrix is generated; Based on the configured probability matrix, the state transition and observation probability matrices are iteratively optimized using the probability optimization formula: Adjust the probability parameters of each state, simulate the changes in geographical state, and generate geographical state probability analysis results; Among them, λ n Represents the critical adjustment coefficient of the nth state, p n Represents the initial probability value of the state before adjustment, which is the original state probability calculated by the model based on the observed data, and N represents the total number of states in the model.

7. The electronic map making method based on basic geographic information data according to claim 6, characterized in that: The steps for obtaining the real-time data fusion analysis results are specifically as follows: Integrate the geographic state probability analysis results with traffic flow data, incorporate climate change information, create a multidimensional data framework through data alignment and format unification, prepare normalized input vectors for multiple regression analysis, and generate a primary data framework for comprehensive analysis; Based on the primary data framework of the comprehensive analysis, perform a multiple regression analysis to determine the relevance and predictive strength of the influencing factors, repeatedly adjust the model parameters until the optimal fit is achieved, and obtain the adjusted regression model parameters; The contribution of each variable is calculated based on the adjusted regression model parameters, using the stability test formula: After the data reaches a stable state, the iteration is stopped and real-time data fusion analysis results are generated; Among them, c i Represents the adjustment coefficient of the i-th variable, which is used to adjust the influence weight of the variable in the model, V i Represents the variable value, which is the numerical value extracted from the data set and used as the actual input data in the regression analysis. i It is the nonlinear adjustment index of the variable, which is used to increase the matching of the model to the nonlinear characteristics of the data. ∈ is a very small constant.

8. The electronic map making method based on basic geographic information data according to claim 7, characterized in that: The steps of recording the automatic map correction number are specifically as follows: Extracting key indicators that affect map parameters, including changes in road usage frequency and building conditions, based on the real-time data fusion analysis results, and generating an initial data set for map parameter adjustment; Automatically updating the road width and building status in a map database using the initial data set for map parameter adjustment to obtain an updated map parameter configuration; According to the updated map parameter configuration, perform automatic correction, record the data and time of each parameter change, and use the formula: Generate map automatic correction data; Among them, α i Represents the adjustment coefficient of the road width parameter, which is the weight of dynamically adjusting the road width according to the road usage frequency data. i Road usage data refers to the road traffic or usage frequency collected in real time, β i is the adjustment coefficient of building status parameters, B i Represents building status data, including building maintenance, damage level, or update frequency, γ i is the time sensitivity adjustment coefficient, which is used to adjust the influence of time variables, T i Indicates a time period, reflecting the time that has passed since the last update.

Images