Classification and association integration method for land use approval data

Abstract

The present invention relates to a method for classifying, associating and integrating land use approval data, and to the technical field of data processing. The method comprises: performing data standardization on original land use approval data to obtain standardized land use approval data; determining a classification score value of the land use approval data; determining an association strength value representing the association between the land use approval data according to the classification score value of each land use approval data; determining an integration evaluation value for integrating the land use approval data according to the association strength value, and integrating the land use approval data based on the integration evaluation value to obtain an integration result; determining a quality score of the integration result according to the integration evaluation value of the integration result; analyzing the integration result and the quality score and feedback information of the integration result to obtain an analysis result, and optimizing the integration result based on the analysis result to obtain a target integration result. The present invention can improve the efficiency and timeliness of land use approval.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method for classifying, associating and integrating land use approval data. Background Art

[0002] In the field of land use approval, existing data processing methods usually rely on traditional database management systems and rule-based classification algorithms. These methods usually involve manual review, data entry and classification of land use approval applications, and then store the information in a centralized database.

[0003] However, due to the diverse sources and formats of land use approval data, existing methods often fail to achieve efficient cross-departmental and cross-system data integration. In addition, the manual review process is not only time-consuming, but also prone to human errors, resulting in reduced approval efficiency and delayed information updates. Summary of the invention

[0004] In view of the technical problems existing in the prior art, the present invention provides a land use approval data classification association integration method which can improve the efficiency and timeliness of land use approval.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] The present invention provides a method for classifying, associating and integrating land use approval data, the method comprising:

[0007] Standardize the original land use approval data to obtain standardized land use approval data;

[0008] Determine the classification score value of the land use approval data;

[0009] Determining, according to the classification score values ​​of the land use approval data, a correlation strength value representing the correlation between the land use approval data;

[0010] Determining, according to the association strength value, an integration evaluation value for integrating the land use approval data, and integrating the land use approval data based on the integration evaluation value to obtain an integration result;

[0011] Determining a quality score of the integration result according to the integration evaluation value of the integration result;

[0012] The integration result and the quality score and feedback information of the integration result are analyzed to obtain an analysis result, and the integration result is optimized based on the analysis result to obtain a target integration result.

[0013] Optionally, the step of normalizing the original land use approval data to obtain standardized land use approval data includes:

[0014] After data cleaning, unit and format unification, and normalization processing are performed on the original land use approval data, first intermediate data is obtained;

[0015] Performing feature scaling and weighting adjustment on the first intermediate data to obtain second intermediate data;

[0016] Performing a standardized formula conversion on the second intermediate data to obtain third intermediate data;

[0017] The third intermediate data is verified and checked, and abnormal values ​​in the third intermediate data are removed or corrected to obtain the land use approval data.

[0018] Optionally, determining the classification score of the land use approval data includes:

[0019] Obtain the evaluation parameter value and dynamic correction factor of the k-th land use approval data;

[0020] Obtaining a similarity score between the k-th land use approval data and other land use approval data, and a threshold reference value of the similarity score;

[0021] Obtaining the feature matching degree between the k-th land use approval data and the target classification feature, and the feature matching degree between the k-1-th land use approval data and the target classification feature;

[0022] According to the first weight and the second weight, combined with the evaluation parameter value of the kth land use approval data, the dynamic correction factor, the similarity score with other land use approval data, the threshold reference value of the similarity score, the feature matching degree with the target classification feature, and the feature matching degree between the k-1th land use approval data and the target classification feature, the classification score value of the land use approval data is determined.

[0023] Optionally, determining the correlation strength value representing the correlation between the land use approval data according to the classification score value of each land use approval data includes:

[0024] Obtaining an association correction factor for adjusting the association strength value, which is used to control the time series attenuation coefficient of the association strength value changing over time, and the time interval between each of the land use approval data;

[0025] Extracting a first associated element value and a second associated element value from the land use approval data, and determining a decay rate of each associated element value;

[0026] Acquire data characteristic values ​​of each of the land use approval data, and adjustment parameters for controlling the difference of the data characteristic values ​​of each of the land use approval data on the correlation strength;

[0027] According to the classification score value, correlation correction factor, time series attenuation coefficient, time interval, first correlation element value, second correlation element value, attenuation rate, data characteristic value and adjustment parameter of each of the land use approval data, the correlation strength value representing the correlation between each of the land use approval data is determined.

[0028] Optionally, determining, according to the association strength value, an integration evaluation value for integrating the land use approval data, includes:

[0029] Obtaining the system compatibility coefficient, data integrity weight, error term, quality assessment index and assessment parameter value of each of the land use approval data;

[0030] Obtaining the correlation strength value between each of the land use approval data;

[0031] Obtaining adjustment parameters, fluctuation attenuation coefficients and dynamic correction factors for calculating the integration evaluation value;

[0032] According to the system compatibility coefficient, data integrity weight, error term, quality assessment index and assessment parameter value of each land use approval data, the correlation strength value between each land use approval data, and the adjustment parameter, the fluctuation attenuation coefficient and the dynamic correction factor, the integration evaluation value of the integration between each land use approval data is determined.

[0033] Optionally, the integration evaluation value is expressed as:

[0034]

[0035] in, is the integration evaluation value, is the system compatibility coefficient of the k-th land use approval data, is the data integrity weight of the k-th land use approval data, is the error term of the k-th land use approval data, is the quality assessment index of the k-th land use approval data, is the quality assessment index of the k-1th land use approval data, is the strength of association, is the adjustment parameter, is the attenuation coefficient, is the evaluation parameter value of the k-th land use approval data, is the dynamic correction factor.

[0036] Optionally, determining the quality score of the integration result according to the integration evaluation value of the integration result includes:

[0037] Obtaining the verification index value of the data point corresponding to the integration result and the maximum value of the verification index value;

[0038] Obtaining the time and evaluation period for evaluating the integration results;

[0039] A first control parameter, a second control parameter, a third control parameter and a first adjustment coefficient for adjusting the quality score of the integration result are obtained.

[0040] Optionally, the quality score is expressed as:

[0041]

[0042] in, is the quality score, is the verification indicator value, is the maximum value of the verification indicator, t is the time, T is the evaluation period, is the first control parameter, is the second control parameter, is the third control parameter, is the second adjustment coefficient.

[0043] Optionally, analyzing the integration result and the quality score and feedback information of the integration result to obtain an analysis result, and optimizing the integration result based on the analysis result to obtain a target integration result includes:

[0044] Outputting the integration result and the quality score and feedback information of the integration result to a unified data platform for analysis to obtain the analysis result;

[0045] Establish an adaptive optimization mechanism;

[0046] The integration result is continuously optimized based on the adaptive optimization mechanism and the analysis result to obtain the target integration result.

[0047] The beneficial effects of the present invention are:

[0048] (1) The present invention designs an intelligent classification and scoring mechanism to accurately classify and score data based on the feature matching degree, similarity score and dynamic correction factor of the data. The scoring mechanism can improve the accuracy and flexibility of classification, significantly reduce the deviation caused by human judgment, and reduce the time of classification processing.

[0049] (2) The present invention uses a correlation quantification model to comprehensively consider the influence of time series decay, data feature similarity and classification score, and dynamically calculates the correlation strength value between data. The model can quantify the degree of correlation between different land use approval data, thereby revealing the potential connection between the data, providing more accurate correlation results for subsequent analysis, and enhancing the synergy between data.

[0050] (3) The present invention optimizes the integration effect between different data sources by combining system compatibility, data integrity and integration score through cross-system integration optimization function, thus realizing cross-department and cross-platform data integration. The optimization function can dynamically adjust the integration degree between data, so that the data maintains efficient and stable compatibility during the integration process, thereby improving the reliability of cross-system data integration.

[0051] In summary, the present invention realizes efficient, accurate and intelligent processing of land use approval data through a comprehensive process design of standardization, intelligent classification, correlation analysis, integrated optimization and quality monitoring, greatly improves data management efficiency, ensures data quality, and provides strong technical support for the integration, analysis and application of land use approval data. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 A flow chart of a land use approval data classification association integration method provided by the present invention;

[0053] Figure 2 A structural diagram of a land use approval data classification association integration system provided by the present invention;

[0054] Figure 3 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0055] Figure 4 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0057] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0058] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0059] See also Figure 1 , provides a flow chart of a land use approval data classification association integration method of the present invention, comprising the following steps:

[0060] Step 201: Standardize the original land use approval data to obtain standardized land use approval data.

[0061] In some embodiments, step 201 may include:

[0062] After data cleaning, unit and format unification, and normalization processing are performed on the original land use approval data, first intermediate data is obtained;

[0063] Performing feature scaling and weighting adjustment on the first intermediate data to obtain second intermediate data;

[0064] Performing a standardized formula conversion on the second intermediate data to obtain third intermediate data;

[0065] The third intermediate data is verified and checked, and abnormal values ​​in the third intermediate data are removed or corrected to obtain the land use approval data.

[0066] In the specific implementation, data cleaning is the first step of the standardization process, which is used to deal with missing values, outliers and redundant data in the original land use approval data to ensure the integrity and accuracy of the data. The quality of the data can be improved by filling missing values ​​and deleting abnormal data. In the cleaned data, different data sources may use different units (such as square meters, hectares, etc.) or different date formats. Unify these units and formats to ensure that the data has a consistent scale and format in subsequent steps, which is convenient for the integration and analysis of different data sources. Normalization is to scale the data to a specified range (such as 0 to 1 or -1 to 1) so that the value ranges of different data features are the same. Normalization can be achieved through methods such as minimum-maximum normalization and Z-score standardization, so that the impact of different features on the analysis results is relatively balanced. After completing the above processing, the first intermediate data is obtained, which is a set of land use approval data with unified format, unit and scale, with high quality and consistency.

[0067] Feature scaling is the process of adjusting between different features to ensure that each feature has an appropriate weight in data analysis and models. This step scales the values ​​of each feature according to actual needs so that the scale difference will not affect the results in subsequent analysis. Different features are given certain weights, and the feature data is weighted according to the weight parameters set in the scheme. For example, more important features can be given greater weights to make them more influential in subsequent standardization and integrated analysis. The second intermediate data is obtained through feature scaling and weighted adjustment. The feature values ​​of this data set have been adjusted according to actual application needs to ensure that key features can be effectively reflected in subsequent analysis.

[0068] In some embodiments, the second intermediate data can be further processed to generate standardized data that meets specific standards, and then the third intermediate data can be checked to ensure that it meets the quality standards. Verification includes checking the value range, distribution characteristics, etc. of the data to ensure that the standardized data does not have abnormalities due to conversion or calculation errors. If abnormal values ​​(such as data points that deviate from the normal range) are found during the verification process, they are processed as needed. Abnormal data can be removed by deletion, correction or interpolation to ensure the integrity and accuracy of the data set. After verification and verification, the final land use approval data is obtained, which meets the standardization requirements and is strictly quality-controlled, and can be directly used in subsequent classification, association and integrated analysis steps.

[0069] In summary, the entire standardization process of the present invention includes steps such as data cleaning, format unification, feature scaling, weighted adjustment, standardized conversion, and final verification and validation. Through these steps, the original land use approval data can be converted into land use approval data with unified structure, standardization, and high quality, providing a reliable data foundation for subsequent analysis, integration, and decision-making.

[0070] Step 202: Determine the classification score of the land use approval data.

[0071] In some embodiments, step 202 may include:

[0072] Obtain the evaluation parameter value and dynamic correction factor of the k-th land use approval data;

[0073] Obtaining a similarity score between the k-th land use approval data and other land use approval data, and a threshold reference value of the similarity score;

[0074] Obtaining the feature matching degree between the k-th land use approval data and the target classification feature, and the feature matching degree between the k-1-th land use approval data and the target classification feature;

[0075] According to the first weight and the second weight, combined with the evaluation parameter value of the kth land use approval data, the dynamic correction factor, the similarity score with other land use approval data, the threshold reference value of the similarity score, the feature matching degree with the target classification feature, and the feature matching degree between the k-1th land use approval data and the target classification feature, the classification score value of the land use approval data is determined.

[0076] In some embodiments, the classification score value of the land use approval data can be expressed as:

[0077]

[0078] in, is the classification score value, is the evaluation parameter value of the k-th land use approval data, is the dynamic correction factor, is the similarity score, is the threshold reference value, is the feature matching degree between the k-th land use approval data and the target classification feature, is the feature matching degree between the k-1th land use approval data and the target classification feature, is the first weight, is the second weight.

[0079] In the specific implementation, Cs is an indicator for scoring the classification results of land use approval data, with the purpose of measuring the rationality and accuracy of the classification. The higher the value, the more the classification result meets the expected evaluation criteria and similarity.

[0080] It is the first weight, which is used to adjust the overall importance of the score and ensure that different data dimensions are reasonably reflected in the score. The value can increase the weight of the overall rating value.

[0081] is a product expression evaluating to parameters. It involves the following two parts:

[0082] It represents the specific parameter value of the k-th land use approval data in the evaluation process. Different data feature values ​​are assigned different weights to reflect the importance of the data in the classification. It is used to make dynamic adjustments based on real-time conditions. For example, when data features fluctuate slightly, it ensures fine-tuning of classification scores, thereby enhancing the adaptability and stability of the scores.

[0083] It is an exponential correction term used to adjust the accuracy of the score based on the similarity score Rs and the threshold reference value Rt. Rs represents the similarity score between the current data and the target category or other data. The higher the value, the higher the similarity between the data. Rt is used as a benchmark value to determine whether the similarity score reaches the ideal similarity standard. If the Rs value is close to or higher than Rt, the classification score will be improved.

[0084] is the second weight, which is used to control the impact of the subsequent feature matching difference part on the score to balance the sensitivity in classification.

[0085] Represents the cumulative sum of the feature matching differences between the current data point and the previous data point. This item is used to measure the continuity and consistency of data in time series or steps.

[0086] It represents the matching degree between the k-th land use approval data and the target classification characteristics. The higher the matching degree, the closer the data is to the target characteristics. is the feature matching degree of the k-1th land use approval data, which is used to Compare and evaluate the change in matching between adjacent data points. The cumulative difference reflects the stability of the entire dataset during the classification process.

[0087] Partially by evaluating parameters The basic score is calculated by multiplying the cumulative product of . This part is directly related to the specific parameters and correction factors of the data, ensuring that the classification score is highly correlated with the characteristic values ​​of the current data.

[0088] Used to adjust the basic value of the score. The ratio of the similarity score Rs and the threshold Rt will affect the result of the exponential function. The higher the index value, the closer the data is to the target standard. The denominator of the formula It is used to smooth the classification score value, evaluate the consistency of the data in the time series by accumulating the difference in feature matching, and avoid affecting the stability of the score due to excessive fluctuations. This part prevents the score from rising abnormally due to poor continuity of data.

[0089] In summary, the formula of the present invention is a dynamic classification scoring system as a whole, which can dynamically adjust the scoring value according to the evaluation parameter value and similarity score of the data, and suppress the volatility of the scoring by changing the feature matching degree. In practical applications, the various coefficients in the formula can be adjusted according to specific classification requirements to optimize the applicability and stability of the classification scoring, and ensure that the scoring results can accurately reflect the degree of conformity between the data and the target features.

[0090] Step 203: Determine, according to the classification score value of each piece of land use approval data, a correlation strength value representing the correlation between each piece of land use approval data.

[0091] In some embodiments, step 203 may include:

[0092] Obtaining an association correction factor for adjusting the association strength value, which is used to control the time series attenuation coefficient of the association strength value changing over time, and the time interval between each of the land use approval data;

[0093] Extracting a first associated element value and a second associated element value from the land use approval data, and determining a decay rate of each associated element value;

[0094] Acquire data characteristic values ​​of each of the land use approval data, and adjustment parameters for controlling the difference of the data characteristic values ​​of each of the land use approval data on the correlation strength;

[0095] According to the classification score value, correlation correction factor, time series attenuation coefficient, time interval, first correlation element value, second correlation element value, attenuation rate, data characteristic value and adjustment parameter of each of the land use approval data, the correlation strength value representing the correlation between each of the land use approval data is determined.

[0096] In some embodiments, the correlation strength value of the correlation between the land use approval data can be expressed as:

[0097]

[0098] Where R is the correlation strength value, is the time series attenuation coefficient, is the time interval, is the first associated element value, is the second associated element value, is the decay rate, Ω is the associated correction factor, is the classification score value, is the adjustment parameter, is the data characteristic value of the k-th land use approval data, It is the data characteristic value of the k-1th land use approval data.

[0099] In the specific implementation, R is used to represent the correlation strength value between land use approval data. The larger the value, the stronger the correlation between different data points. This value plays a key role in correlation analysis and helps to measure the correlation and relationship strength between data.

[0100] It is used to control the decay speed of the correlation strength over time, and is usually used to consider the impact of the time gap between data on the correlation. When it is large, the time series decay coefficient reduces the association strength to match the impact of time distance in real data.

[0101] is the interval between two data points in the time series, usually used to reflect the time lag effect. As it increases, the strength of the association will be affected by the time series decay coefficient and decreased due to the influence of.

[0102] and Represent the first associated element value and the second associated element value respectively. The associated elements are related features or variables in the land use approval data, and the association relationship between the elements is calculated through their inner product.

[0103] is the decay rate that controls data association, with Adjusts how quickly the strength of the association decreases over time. A value of will cause the correlation to weaken rapidly as the time interval increases.

[0104] The correlation correction factor is used to adjust the correlation strength based on the additional conditions in the specific application to make it more suitable for the specific correlation analysis. For example, it can be adjusted based on external factors such as geographical location and department.

[0105] Cs is derived from the classification scoring mechanism and represents the classification score of the current data. By introducing Cs, the formula links the classification score with the association strength, thereby adjusting the association of the data. If the classification score is high, the association will also increase accordingly.

[0106] It is used to control the impact of eigenvalue differences on the strength of association, making the formula's sensitivity to differences in eigenvalues ​​of different data adjustable.

[0107] Represent the eigenvalues ​​of the kth and k-1th data respectively. The absolute difference of the eigenvalues , we can evaluate the changes in the characteristics of two data. The larger the difference, the lower the correlation between the two data in terms of the characteristic values, thus reducing the strength of the association.

[0108] The first part of the formula Used to control the correlation degree over time interval Increased decay effect. Increase, exponential term Gradually approaches zero, thereby reducing the correlation strength R, simulating the weakening of the correlation of real data over time.

[0109] Middle part The normalized inner product between the two elements is calculated to measure the similarity between the two elements X and Y. The values ​​calculated in this part can be regarded as the "similarity" between the elements. By multiplying and normalizing the two elements, a correlation measure is obtained.

[0110] It is a correction factor used to further fine-tune the association strength value R according to specific association requirements, so as to adapt the association analysis to specific situational requirements.

[0111] The last part of the formula It is used to combine the classification score Cs and the feature value difference. The classification score Cs is the score derived from the classification step. When Cs is higher, it means that the classification effect of the data is better, and the association strength will also increase accordingly.

[0112] This item is used to suppress the volatility of the correlation strength. If the eigenvalue changes greatly, it means that the difference in data characteristics leads to a lower correlation, which in turn weakens the correlation strength. , the effect of eigenvalue differences on association strength can be appropriately controlled.

[0113] Time decay coefficient and time interval The exponential decay of simulating the decreasing trend of data association over time. It is used to measure the similarity of associated elements and ensure that the association analysis reflects the consistency of two data points in specific elements. The classification score Cs provides feedback on the classification step, links the classification effect with the association strength, and realizes a dynamic association adjustment mechanism. By controlling the impact of eigenvalue differences, the effect of data feature changes on association strength can be smoothed in the formula, thereby reducing fluctuations in association values ​​caused by feature mutations.

[0114] In summary, the present invention realizes the comprehensive correlation analysis of multiple factors such as time, element similarity, classification score, characteristic value change, etc. By adjusting various parameters, the correlation strength can be optimized according to different land use approval data requirements.

[0115] Step 204: Determine an integration evaluation value for integrating the land use approval data according to the association strength value, and integrate the land use approval data based on the integration evaluation value to obtain an integration result.

[0116] In some embodiments, step 204 may include:

[0117] Obtaining the system compatibility coefficient, data integrity weight, error term, quality assessment index and assessment parameter value of each of the land use approval data;

[0118] Obtaining the correlation strength value between each of the land use approval data;

[0119] Obtaining adjustment parameters, fluctuation attenuation coefficients and dynamic correction factors for calculating the integration evaluation value;

[0120] According to the system compatibility coefficient, data integrity weight, error term, quality assessment index and assessment parameter value of each land use approval data, the correlation strength value between each land use approval data, and the adjustment parameter, the fluctuation attenuation coefficient and the dynamic correction factor, the integration evaluation value of the integration between each land use approval data is determined.

[0121] In some embodiments, the integration evaluation value is expressed as:

[0122]

[0123] in, is the integration evaluation value, is the system compatibility coefficient of the k-th land use approval data, is the data integrity weight of the k-th land use approval data, is the error term of the k-th land use approval data, is the quality assessment index of the k-th land use approval data, is the quality assessment index of the k-1th land use approval data, is the strength of association, is the adjustment parameter, is the attenuation coefficient, is the evaluation parameter value of the k-th land use approval data, is the dynamic correction factor.

[0124] In the specific implementation, It is an integration evaluation value, which is used to quantify the scoring index of data integration effect. The higher the value, the better the integration effect of system data, which reflects the compatibility, integrity and integration quality of data association of different data sources.

[0125] Adjust the weight factor of the overall output result of the formula to control the basic weight of the integration. Values ​​indicate a higher emphasis on integration.

[0126] They respectively represent the system compatibility coefficient and data integrity weight of the k-th land use approval data. It is the system compatibility coefficient, which is used to evaluate the compatibility of the current data source in the integrated system. The more compatible the data source is, the more conducive it is to the overall system integration. It is the data integrity weight, which measures the completeness and accuracy of the data. Data with higher integrity is more suitable for system integration and improves the integration effect.

[0127] is the error term of the kth land use approval data. The maximum value of each data error is usually taken as the benchmark in the data integration process to measure the accuracy of the system data.

[0128] R is the correlation strength value, which indicates the correlation between different data and is usually derived from the calculation of quantitative analysis of correlation. The higher the value, the closer the data is in logic or characteristics, and the more suitable it is for integration.

[0129] It is used to control the impact of feature matching changes on integration and adjust the sensitivity of feature matching differences in the denominator to the integration effect.

[0130] They represent the quality assessment indicators of the kth and k-1th land use approval data respectively. It is the quality assessment value of the kth land use approval data point, which is used to evaluate the quality control during data integration. It is the quality evaluation value of the k-1th data point, which is used to calculate the quality difference and ensure the stability of the integrated quality. Used to control the attenuation effect of the cumulative evaluation parameters in the formula on the integration degree.

[0131] It is the specific evaluation parameter value of the k-th land use approval data, which is used to measure the adaptability and integration potential of the data. This parameter is a key indicator selected according to system requirements, covering factors such as data source and structure. It is used to adjust the evaluation parameter values ​​in real time according to system changes in actual operation to adapt to changing integration requirements.

[0132] The first part of the formula Indicates the basic integration factor. Through the system compatibility coefficient and data integrity weight The product of the basic integrated value of the data is obtained, and then divided by the maximum value of the error term , in order to standardize the basic integration value. This part reflects the contribution of the compatibility and integrity of each data source to the integration effect.

[0133] The second part of the formula It is used to adjust the integration effect according to the correlation between data and the stability of feature matching. The specific calculation logic is as follows: R represents the correlation between data. Data with high correlation is more suitable for integration, thus increasing the integration evaluation value. Represents the cumulative difference of feature matching. By summing the squares of the differences in feature matching, and first adjusting the coefficient , which can reduce the deviation of the integration effect caused by the fluctuation of matching degree. This ensures that the integration system has a certain robustness to quality changes.

[0134] Final part Used to suppress the impact of evaluation parameter fluctuations on integration effects. is the fluctuation attenuation coefficient, which adjusts the speed of exponential decay.

[0135] Indicates the evaluation parameter value and dynamic correction factor The accumulated value of The accumulation and squaring of and then exponential decay can suppress the large fluctuations of the evaluation parameters to improve the stability of the integration.

[0136] The integrated result refers to the integration of land use approval data from different departments or sources into a unified data set after a series of processing and optimization for subsequent analysis, decision-making and application. The data set corresponding to the integrated result can not only contain the comprehensive information of each data source, but also include the evaluation score for comprehensive evaluation of data quality, relevance and accuracy.

[0137] Just as an example, suppose you have the following data sources:

[0138] Data source 1: land area, land type, land ownership, etc.

[0139] Data source 2: Environmental impact assessment (such as pollutant concentration, ecological impact, etc.).

[0140] Data source 3: Traffic accessibility (such as road density, traffic flow, public transportation services, etc.).

[0141] After integration, the integration results can include the following:

[0142] Comprehensive evaluation indicators: such as a comprehensive "land development suitability score" that combines factors such as land area, environmental impact, and transportation accessibility.

[0143] Land use planning recommendations: Based on the integration results, a land development plan may be generated, suggesting that some land is suitable for development, while some land is not suitable for development due to greater environmental impact or inconvenient transportation.

[0144] Risk assessment: Through integrated analysis, the environmental risks, development risks, etc. of the region are assessed to help decision makers make more scientific judgments.

[0145] The following describes how to determine the integration result based on the integration evaluation value, assuming that the land use approval data comes from the following three departments: Urban planning department: provides information such as the area, use nature, and planned use of the land. Environmental protection department: provides environmental impact assessment data, such as pollutant concentration, ecological damage, etc. Transportation department: provides data such as traffic flow, road density, and public transportation accessibility.

[0146] The data of each department will be standardized and weighted according to the integration evaluation value Is. For example, suppose the data integration of the urban planning department is high (Is=0.8), the data integration of the environmental protection department is low (Is=0.5), and the data integration of the transportation department is medium (Is=0.7). The final integration result will pay more attention to the data of the urban planning department, and combine the data of the environmental protection and transportation departments to obtain a comprehensive "land development suitability assessment data set" and the corresponding "land development suitability score" as the final integration result.

[0147] Step 205: Determine the quality score of the integration result according to the integration evaluation value of the integration result.

[0148] In some embodiments, step 205 may include:

[0149] Obtaining the verification index value of the data point corresponding to the integration result and the maximum value of the verification index value;

[0150] Obtaining the time and evaluation period for evaluating the integration results;

[0151] A first control parameter, a second control parameter, a third control parameter and a first adjustment coefficient for adjusting the quality score of the integration result are obtained.

[0152] In some embodiments, the quality score is expressed as:

[0153]

[0154] in, is the quality score, is the verification indicator value, is the maximum value of the verification indicator, t is the time, T is the evaluation period, is the first control parameter, is the second control parameter, is the third control parameter, is the second adjustment coefficient.

[0155] In the specific implementation, Used to measure the data quality of land use approval data during the integration and processing process. The higher the score, the better the data quality, the more reliable the integrated data is, and it is suitable for further analysis or decision-making.

[0156] The weight used to adjust the overall quality score determines the baseline level of Qs. The higher the value, the higher the overall quality score, thus increasing the emphasis on data quality.

[0157] Used to control the growth rate of the verification index part and affect the verification index The attenuation degree of the cumulative index makes it more suppressive to low-quality data. The larger the value, the more obvious the impact of the cumulative index on the quality score.

[0158] It is the quality verification value of the data point corresponding to the current integration result, and is the basic indicator for measuring data quality, such as the accuracy or completeness of the data. Indicates that the data quality is good. The contribution is greater. Used for Standardization is performed to ensure the verification of different data. The range is consistent, making The result is between 0 and 1.

[0159] Used to adjust the time volatility of the quality score so that the quality score can fluctuate periodically over time to meet the needs of different evaluation cycles. This coefficient mainly affects the amplitude of the time fluctuation term.

[0160] T represents a quality assessment period, which is used to calculate the frequency part of the time fluctuation function. The shorter the period, the more frequently the impact of time fluctuation changes.

[0161] t is the time point of the current data, and is used together with T to control the time fluctuation of the quality score.

[0162] Used to control the impact of the integration level Is on the quality score by adjusting It can balance the contribution of integration to Qs. A higher value will reduce the impact of integration on the quality score.

[0163] Is is the score value from the integration step, which indicates the integration quality of the current data. The higher the integration, the better the compatibility and consistency of data between systems, which has a positive impact on data quality.

[0164] The first part of the formula Used to give a basic quality score of the data based on the standardized cumulative value of the validation indicator.

[0165] :First, verify the indicator value Normalization ensures that validation values ​​for different data are within the same range for comparison.

[0166] : Accumulate the normalized validation index values ​​to form an overall evaluation of the validation index.

[0167] : The impact of cumulative verification indicators on the quality score is controlled through exponential decay to ensure that low-quality data has a suppressive effect on the overall score.

[0168] The second part of the formula Used to introduce time volatility.

[0169] : Generate a sinusoidal fluctuation that changes with time period, simulate the fluctuation of data quality at different time points, and adapt to the periodic changes of data.

[0170] :By controlling the parameters Adjust the amplitude of the fluctuation. A higher value means that temporal fluctuations have a more significant impact on the quality score.

[0171] The third part of the formula It is the reverse smoothing control of the integration evaluation value Is.

[0172] :Adjust the impact of integration Is on the quality score. Data with higher integration has a positive effect on the overall quality score.

[0173] : If I is high, the term approaches 0, improving the quality score; if Is is low, the quality score is reduced. This design ensures that the integration effect of the data has a direct impact on the quality.

[0174] pass The validation index of the data forms a basic contribution to the quality score. The higher the validation index, the closer the exponent term is to 1, which increases the quality score.

[0175] Time Fluctuation Term Simulate the fluctuation characteristics of data quality at different time points to ensure the adaptability of quality assessment within the cycle and the ability to cope with periodic changes in data in actual scenarios.

[0176] The last item The integration The impact on the quality score is smoothly controlled. When the integration level is high, the denominator tends to 1, which improves the quality score; the opposite is true when the integration level is low, thus forming a feedback loop of the impact of the integration level on data quality.

[0177] In summary, the present invention combines the influence of multiple factors such as verification indicators, time fluctuations, and integration to form a dynamic quality scoring mechanism. , , and Etc., it can flexibly adapt to the quality change requirements and periodic change requirements of different data sources, making the quality score more accurate and applicable.

[0178] Step 206: Analyze the integration result and the quality score and feedback information of the integration result to obtain an analysis result, and optimize the integration result based on the analysis result to obtain a target integration result.

[0179] In some embodiments, step 206 may include:

[0180] Outputting the integration result and the quality score and feedback information of the integration result to a unified data platform for analysis to obtain the analysis result;

[0181] Establish an adaptive optimization mechanism;

[0182] The integration result is continuously optimized based on the adaptive optimization mechanism and the analysis result to obtain the target integration result.

[0183] In the specific implementation, the integration results, quality scores and feedback information can be output to a unified data platform for analysis, and then the integration results can be dynamically optimized through the adaptive optimization mechanism. The integration result can be a set of highly consistent and compatible data sets formed after the multi-source land use approval data is standardized, classified, associated and integrated. The integration result reflects the fusion effect of different data sources on a unified platform.

[0184] The quality score is calculated by the quality monitoring module and indicates the overall data quality and consistency of the integrated results. The quality score reflects the accuracy and reliability of the data during standardization, classification and integration, providing quality assurance for data analysis.

[0185] Feedback information includes feedback data automatically generated by users or systems on the actual performance and usage of the integration results, such as data accuracy, whether it meets usage requirements, etc. Feedback information can reveal deficiencies in the integration results and provide reference for subsequent improvements.

[0186] The above data can be exported to a unified data platform for centralized management and analysis. The unified data platform can intuitively display the integration results and quality scores through data visualization, statistical analysis and other functions, so as to further explore potential problems and optimization directions in data integration.

[0187] The adaptive optimization mechanism is a dynamic adjustment system that automatically optimizes integration parameters based on feedback and analysis results during the data integration process. The mechanism can respond to changes in data quality scores and feedback information in real time, and automatically adjust parameters in the standardization, classification, association, and integration processes to ensure that the integration results are continuously improved.

[0188] The adaptive optimization mechanism will use algorithms to automatically adjust parameters in each processing link based on the analysis results of the data platform, such as weight coefficients in data standardization, dynamic correction factors in intelligent classification scoring, and adjustment parameters in association strength, thereby improving the overall integration effect and quality.

[0189] The analysis results on the data platform show the quality and performance of the integration results. For example, if the analysis results show that some data sources have large errors or poor compatibility in the integration, the adaptive optimization mechanism can perform targeted optimization based on this information.

[0190] The adaptive optimization mechanism analyzes the integration results, quality scores and feedback information to identify weak links in the integration process and adjust the standardization, classification and integration algorithm parameters. The optimization process is continuous, which means that the integration results after each optimization can be further fed back to the platform to form a closed loop and continuously improve the data integration effect.

[0191] After a series of optimization and adjustments, the quality and consistency of the integrated results are gradually improved, and finally the target integrated results that meet expectations are formed. The target integrated results have the characteristics of high quality, strong stability, and good compatibility, and can provide reliable data support for land use approval decisions.

[0192] As an example only, each data source has been standardized and preprocessed (cleaned, unit unified, normalized, feature scaled, etc.).

[0193] Calculate the integration evaluation value Is, for example:

[0194] Data source 1 (urban planning department): The integration degree Is1=0.8, and the data weight is relatively high because of its strong data compatibility and wide coverage.

[0195] Data source 2 (Environmental Protection Department): Integration degree Is2=0.6. Due to the low quality of some data, the contribution is low.

[0196] Data source 3 (transportation department): Integration degree Is3=0.7, data quality and correlation are medium.

[0197] Perform weighted integration of each data source according to the formula: D=(Is1⋅D1+Is2⋅D2+Is3⋅D3) / (Is1+Is2+Is3).

[0198] Among them, D is the preliminary integration result, including comprehensive land development suitability score, environmental risk score, traffic accessibility score, etc. The preliminary integration result D, integration quality score and feedback information can be uploaded to the unified data platform. The data quality of the integration result can be scored, for example:

[0199] Data integrity score: 90 / 100, data consistency score: 85 / 100, overall quality score: 87 / 100.

[0200] Feedback information: Based on user usage or expert evaluation, the following issues can be reported: The concentration of pollutants in some areas of the environmental protection data is relatively large. The road density in the transportation data is not fully covered.

[0201] In some embodiments, the unified data platform performs multi-dimensional analysis on the integration results, including:

[0202] Data source contribution analysis: Analyzing the impact of different data sources on the integrated results, it was found that the environmental assessment indicators of data source 2 contributed less to the overall results.

[0203] Identification of quality issues: Anomalies or deficiencies in detection data, for example, some transportation data lacks public transportation coverage in certain areas. Pollutant concentration values ​​in environmental assessment data fluctuate greatly, affecting the credibility of the overall assessment results.

[0204] In some embodiments, an adaptive optimization mechanism may be developed based on the analysis results:

[0205] For example, the optimization direction could be: increasing the contribution weight of low-quality data sources, correcting outliers in environmental assessment data, and introducing supplementary data (e.g. updating data from the transportation department to cover missing areas).

[0206] The optimization strategies can be:

[0207] Adjust the weight parameters of the integration evaluation value formula to correct the impact of low-quality data sources. Use dynamic correction factors to dynamically adjust data with large deviations. Enhance the linkage mechanism of feedback and analysis, and continuously optimize the subsequent data processing process.

[0208] In some embodiments, abnormal pollutant concentration values ​​in environmental assessment data can be repaired, and missing public transportation coverage indicators in transportation data can be supplemented.

[0209] In some embodiments, the integration weights can be reallocated, for example, the weight of environmental protection data (data source 2) is increased from 0.6 to 0.7, reflecting the increased contribution of the optimized data. The adjustment parameters in the correlation strength formula are modified so that data sources with stronger correlation have a higher impact on the integration results.

[0210] Through continuous optimization, the integration results are more accurate and comprehensive. The target integration results may include:

[0211] Land development suitability score: This is a combination of urban planning, environmental assessment and transportation accessibility indicators. For example, the suitability score of a piece of land is 92 / 100.

[0212] Environmental risk analysis: Based on the revised environmental assessment data, the pollution risk of a certain plot of land is assessed to be low.

[0213] Transportation accessibility score: Combined with the supplementary data, the transportation accessibility of a certain area is improved to 85 / 100.

[0214] In summary, the present invention achieves continuous optimization of the integration results of land use approval data by aggregating the integration results, quality scores and feedback information on a unified platform, and combining them with an adaptive optimization mechanism for analysis and dynamic adjustment. The results after each optimization are fed back and adjusted through the data platform and optimization mechanism to ensure that the final target integration results meet the requirements of high quality, accuracy and reliability. By uploading the integration results, their quality scores and feedback information to a unified data platform for analysis, and adjusting the data processing flow and integration strategy through an adaptive optimization mechanism, the formation of the target integration results is finally achieved. The target integration results are not only more comprehensive and reliable, but also can provide stronger support for land use approval decisions.

[0215] See also Figure 2 , Figure 2 A structural diagram of a land use approval data classification association integration system provided by the present invention.

[0216] like Figure 2 As shown, a land use approval data classification association integration system proposed in an embodiment of the present invention includes:

[0217] The data processing module 301 is used to standardize the original land use approval data to obtain standardized land use approval data;

[0218] A classification scoring module 302 is used to determine the classification scoring value of the land use approval data;

[0219] The data association module 303 is used to determine the association strength value representing the association between each piece of land use approval data according to the classification score value of each piece of land use approval data;

[0220] The first integration module 304 is used to determine the integration evaluation value of the land use approval data according to the association strength value, and integrate the land use approval data based on the integration evaluation value to obtain an integration result;

[0221] A quality evaluation module 305, configured to determine a quality score of the integration result according to an integration evaluation value of the integration result;

[0222] The second integration module 306 is used to analyze the integration result and the quality score and feedback information of the integration result to obtain an analysis result, and optimize the integration result based on the analysis result to obtain a target integration result.

[0223] See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented:

[0224] Standardize the original land use approval data to obtain standardized land use approval data;

[0225] Determine the classification score value of the land use approval data;

[0226] Determining, according to the classification score values ​​of the land use approval data, a correlation strength value representing the correlation between the land use approval data;

[0227] Determining, according to the association strength value, an integration evaluation value for integrating the land use approval data, and integrating the land use approval data based on the integration evaluation value to obtain an integration result;

[0228] Determining a quality score of the integration result according to the integration evaluation value of the integration result;

[0229] The integration result and the quality score and feedback information of the integration result are analyzed to obtain an analysis result, and the integration result is optimized based on the analysis result to obtain a target integration result.

[0230] See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 500, on which a computer program 411 is stored. When the computer program 411 is executed by a processor, the following steps are implemented:

[0231] Standardize the original land use approval data to obtain standardized land use approval data;

[0232] Determine the classification score value of the land use approval data;

[0233] Determining, according to the classification score values ​​of the land use approval data, a correlation strength value representing the correlation between the land use approval data;

[0234] Determining, according to the association strength value, an integration evaluation value for integrating the land use approval data, and integrating the land use approval data based on the integration evaluation value to obtain an integration result;

[0235] Determining a quality score of the integration result according to the integration evaluation value of the integration result;

[0236] The integration result and the quality score and feedback information of the integration result are analyzed to obtain an analysis result, and the integration result is optimized based on the analysis result to obtain a target integration result.

[0237] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0238] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0239] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0240] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0241] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0242] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0243] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A land use approval data classification association integration method, characterized in that: The method comprises: Standardize the original land use approval data to obtain standardized land use approval data; Determine the classification score value of the land use approval data; the classification score value of the land use approval data can be expressed as: Among them, Cs is the classification score, P k is the evaluation parameter value of the k-th land use approval data, is the dynamic correction factor, Rs is the similarity score, Rt is the threshold reference value, M k is the feature matching degree between the k-th land use approval data and the target classification feature, M k-1 is the feature matching degree between the k-1th land use approval data and the target classification feature, θ is the first weight, and δ is the second weight; According to the classification score value of each of the land use approval data, a correlation strength value representing the correlation between each of the land use approval data is determined; the correlation strength value representing the correlation between each of the land use approval data can be expressed as: Among them, R is the correlation strength value, ρ is the time series decay coefficient, Δt is the time interval, and X i is the first associated factor value, Y i is the second correlation factor value, μ is the decay rate, Ω is the correlation correction factor, Cs is the classification score value, α is the adjustment parameter, and F k is the data characteristic value of the k-th land use approval data, F k-1 is the data characteristic value of the k-1th land use approval data; Determining, according to the association strength value, an integration evaluation value for integrating the land use approval data, and integrating the land use approval data based on the integration evaluation value to obtain an integration result; The quality score of the integration result is determined according to the integration evaluation value of the integration result; the integration evaluation value is expressed as: Among them, Is is the integration evaluation value, A k is the system compatibility coefficient of the k-th land use approval data, B k is the data integrity weight of the k-th land use approval data, E k is the error term of the k-th land use approval data, Q k is the quality evaluation index of the k-th land use approval data, Q k-1 is the quality evaluation index of the k-1th land use approval data, R is the correlation strength, σ is the adjustment parameter, λ is the attenuation coefficient, and P k is the evaluation parameter value of the k-th land use approval data, is the dynamic correction factor; Analyzing the integration result and the quality score and feedback information of the integration result to obtain an analysis result, and optimizing the integration result based on the analysis result to obtain a target integration result; The quality score is expressed as: Where Qs is the quality score, V k is the verification index value, V max is the maximum value of the verification index value, t is the time, T is the evaluation period, ψ is the first control parameter, τ is the second control parameter, ∈ is the third control parameter, and δ is the second adjustment coefficient.

2. The land use approval data classification association integration method according to claim 1 is characterized in that: The process of standardizing the original land use approval data to obtain standardized land use approval data includes: After data cleaning, unit and format unification, and normalization processing are performed on the original land use approval data, first intermediate data is obtained; Performing feature scaling and weighting adjustment on the first intermediate data to obtain second intermediate data; Performing a standardized formula conversion on the second intermediate data to obtain third intermediate data; The third intermediate data is verified and checked, and abnormal values ​​in the third intermediate data are removed or corrected to obtain the land use approval data.

3. The land use approval data classification association integration method according to claim 2 is characterized in that: Determining the classification score of the land use approval data includes: Obtain the evaluation parameter value and dynamic correction factor of the k-th land use approval data; Obtaining a similarity score between the k-th land use approval data and other land use approval data, and a threshold reference value of the similarity score; Obtaining the feature matching degree between the k-th land use approval data and the target classification feature, and the feature matching degree between the k-1-th land use approval data and the target classification feature; According to the first weight and the second weight, combined with the evaluation parameter value of the kth land use approval data, the dynamic correction factor, the similarity score with other land use approval data, the threshold reference value of the similarity score, the feature matching degree with the target classification feature, and the feature matching degree between the k-1th land use approval data and the target classification feature, the classification score value of the land use approval data is determined.

4. The land use approval data classification association integration method according to claim 3 is characterized in that: Determining the correlation strength value representing the correlation between the land use approval data according to the classification score value of each land use approval data includes: Obtaining an association correction factor for adjusting the association strength value, which is used to control the time series attenuation coefficient of the association strength value changing over time, and the time interval between each of the land use approval data; Extracting a first associated element value and a second associated element value from the land use approval data, and determining a decay rate of each associated element value; Acquire data characteristic values ​​of each of the land use approval data, and adjustment parameters for controlling the difference of the data characteristic values ​​of each of the land use approval data on the correlation strength; According to the classification score value, correlation correction factor, time series attenuation coefficient, time interval, first correlation element value, second correlation element value, attenuation rate, data characteristic value and adjustment parameter of each of the land use approval data, the correlation strength value representing the correlation between each of the land use approval data is determined.

5. The land use approval data classification association integration method according to claim 4 is characterized in that: Determining the integration evaluation value of the integration between the land use approval data according to the association strength value includes: Obtaining the system compatibility coefficient, data integrity weight, error term, quality assessment index and assessment parameter value of each of the land use approval data; Obtaining the correlation strength value between each of the land use approval data; Obtaining adjustment parameters, fluctuation attenuation coefficients and dynamic correction factors for calculating the integration evaluation value; According to the system compatibility coefficient, data integrity weight, error term, quality assessment index and assessment parameter value of each land use approval data, the correlation strength value between each land use approval data, and the adjustment parameter, the fluctuation attenuation coefficient and the dynamic correction factor, the integration evaluation value of the integration between each land use approval data is determined.

6. The land use approval data classification association integration method according to claim 5 is characterized in that: Determining the quality score of the integration result according to the integration evaluation value of the integration result includes: Obtaining the verification index value of the data point corresponding to the integration result and the maximum value of the verification index value; Obtaining the time and evaluation period for evaluating the integration results; A first control parameter, a second control parameter, a third control parameter and a first adjustment coefficient for adjusting the quality score of the integration result are obtained.

7. The land use approval data classification association integration method according to any one of claims 1 to 6, characterized in that: The step of analyzing the integration result and the quality score and feedback information of the integration result to obtain an analysis result, and optimizing the integration result based on the analysis result to obtain a target integration result includes: Outputting the integration result and the quality score and feedback information of the integration result to a unified data platform for analysis to obtain the analysis result; Establish an adaptive optimization mechanism; The integration result is continuously optimized based on the adaptive optimization mechanism and the analysis result to obtain the target integration result.

Images