A law enforcement record generation system and method based on multi-source data fusion

Abstract

The present invention relates to the field of data fusion technology, and specifically to a law enforcement record generation system and method for multi-source data fusion, the system comprising: a data acquisition module normalizing and eliminating duplicate data, an anomaly detection module performing data verification and cleaning, a source evaluation module performing quantitative scoring on data sources, a weight adjustment module dynamically adjusting weights based on the scores, a data fusion module performing weighted fusion and field verification, and outputting collaborative law enforcement records. In the present invention, data quality is further ensured by verifying the data value range and calculating the deviation value, and the reliability of the data set is enhanced by removing abnormal data. Through quantitative scoring and dynamic weight adjustment, the quality assessment of the data source and the fairness of the input are ensured, making the law enforcement records more comprehensive and authoritative. This refined data processing not only improves the accuracy of law enforcement records, but also enhances the security and integrity of information, thereby significantly improving the response speed and decision-making quality of law enforcement agencies.

Description

Technical Field

[0001] The present invention relates to the technical field of data fusion, and in particular to a law enforcement record generation system and method for multi-source data fusion. Background Art

[0002] The field of data fusion technology involves methods and systems for integrating and analyzing data from multiple data sources. These technologies allow data from different sources to be combined into a single view, thereby improving decision-making quality and operational efficiency. Data fusion technology is widely used in many fields such as military, security monitoring, medical, environmental monitoring, and business intelligence. In the implementation process, data fusion solves the problems of data redundancy and inconsistency, and cleans, integrates and analyzes data through algorithms and models to provide more accurate and comprehensive information.

[0003] Among them, the law enforcement record generation system refers to the use of data fusion technology to automatically collect, integrate and process data from different law enforcement departments and information systems to generate law enforcement records. The main purpose of this system is to improve law enforcement efficiency and record accuracy, so that law enforcement agencies can respond to and handle incidents quickly while ensuring the integrity and security of information. The law enforcement record generation system is particularly suitable for law enforcement activities that require cross-departmental cooperation and information sharing, such as traffic violation processing, crime investigation and other occasions.

[0004] Existing technologies often face data redundancy and inconsistency problems when processing multi-source data, and lack effective mechanisms to evaluate the reliability and consistency of data sources, resulting in possible errors and delays in law enforcement records. The failure to dynamically evaluate the trust of data sources and adjust weights limits the efficiency of data utilization and the accuracy of law enforcement records. In addition, existing systems often fail to completely exclude abnormal data during data fusion, affecting the quality of decision-making and the efficiency of operations. These deficiencies lead to slow information processing, difficulties in cross-departmental cooperation and information sharing, and reduce the overall efficiency and effectiveness of law enforcement. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a law enforcement record generation system and method with multi-source data fusion.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: A law enforcement record generation system for multi-source data fusion includes:

[0007] The data collection module obtains raw data from multiple data sources, normalizes the raw data, removes duplicate records after comparison, and extracts related data fields including law enforcement officer information, illegal behavior description, time and place, and evidence materials through rule matching to generate integrated raw records;

[0008] The anomaly detection module performs a data value range check on the integrated original records, calculates the deviation value of each data field according to the specified deviation range, marks and removes entries whose deviation values ​​exceed the set standard, reconstructs the data table for the cleaned data, and generates a processed data set;

[0009] The source evaluation module quantitatively scores the numerical distribution, consistency and evidence material coverage of multiple data sources based on the processed data set, obtains an overall scoring result by performing weighted average processing on the scoring set, summarizes the overall scoring result by data source dimension and stores it as an independent record, and establishes a source trust scoring table;

[0010] The weight adjustment module dynamically adjusts the input weight distribution of multiple data sources according to the score data in the source trust score table, performs comparison according to the current characteristics of the input data, allocates weight parameters of multiple sources in combination with the score and data distribution, and obtains the adjusted weight configuration;

[0011] The data fusion and generation module performs weighted fusion on the input data of each data source based on the adjusted weight configuration, performs field verification on the fusion result, eliminates the interference of non-critical data fields on the result based on the weight, and outputs the fields that meet the fusion rules as collaborative law enforcement records.

[0012] The integrated original records include normalized data, deduplicated records, and extracted related fields; the processed data set includes verified data entries, cleaned data with abnormal items removed, and reconstructed data tables; the source trust score table includes source score, coverage data, and consistency score; the adjusted weight configuration includes source weight parameters, score weighting parameters, and distribution weight parameters; the collaborative law enforcement records include weighted fusion data, verified valid fields, and output fields that comply with the rules.

[0013] As a further solution of the present invention, the step of obtaining the integrated original records is specifically as follows:

[0014] After extracting data from multiple data sources, the data is standardized to eliminate the dimension effect and generate a standardized data set;

[0015] Performing uniqueness verification on the standardized data set, comparing the data using a hash function, identifying and deleting duplicate entries, and obtaining a deduplicated data set;

[0016] Using data matching technology, identifying and extracting key fields in the deduplicated data set, including user ID and transaction date, and constructing a related field data set based on the fields;

[0017] Based on the associated field data set, data association analysis is performed and the association degree calculation formula is applied: ;

[0018] Calculate and analyze the correlation between differentiated data fields to generate integrated original records;

[0019] in, Representative The value of a data field is used to represent the value of the field in the data set. Representative The value of a data field is used to represent the value of another field in the data set. It is The weight coefficient of the field is adjusted The influence of each field in the correlation calculation, It is The weight coefficient of the field is adjusted The influence of each field in the correlation calculation, Is seeking The weight coefficient used in the square sum is used to adjust The contribution in the denominator, Indicates Field and The correlation index between fields is used to quantify the strength of the correlation between two fields.

[0020] As a further solution of the present invention, the step of obtaining the processed data set is specifically:

[0021] Performing data value range verification on the integrated original records, checking the compliance of each data point based on the preset standards of each field, verifying the compliance of the data, and generating a data set that meets the standards;

[0022] Based on the data set that meets the standard, calculating the deviation value of each data field, comparing the deviation value with the set deviation range, and generating a deviation value analysis data set;

[0023] Screening all data entries in the deviation analysis data set whose deviation values ​​exceed the standard, marking the entries, and performing a removal operation to obtain a corrected data set;

[0024] The modified data set is processed using the formula: ;

[0025] Calculate the adjusted standardized score for each data point to generate a processed data set;

[0026] in, represents the value of the data point, is the mean value of the data field, is the standard deviation, Used to adjust the score sensitivity, Representative Data points for Adjusted normalized scores for each data field.

[0027] As a further solution of the present invention, the steps of obtaining the information source trust score table are specifically as follows:

[0028] Quantitatively scoring multiple data sources in the processed data set to capture value distribution, consistency, and data coverage, and generating a preliminary scoring result set based on multi-dimensional statistical indicators;

[0029] By performing weighted averaging processing on multiple scores in the preliminary scoring result set, each data source score is assigned a differentiated weight according to its data quality and quantity, and a weighted scoring data set is calculated and generated;

[0030] Summarize the weighted scoring data set according to the data source dimension, aggregate the scoring results of each data source, ensure that the score of the data source can reflect the criticality of the contribution, and obtain a data source summary scoring set;

[0031] Aggregate the score set based on the data source, using the formula: ;

[0032] Calculate the normalized trust of each data source and establish a source trust score table ;

[0033] in, Indicates The ratings of the data sources, According to the data source The weighting factor is determined by the quality and coverage of the

[0034] As a further solution of the present invention, the step of obtaining the adjusted weight configuration is specifically:

[0035] Extracting the score data of each data source from the source trust score table, analyzing the value distribution and consistency, preliminarily determining the weight of each data source based on the data characteristics, and generating a preliminary weight distribution data set;

[0036] Refining the preliminary weight allocation data set, dynamically adjusting the weights according to the current input characteristics of each data source and the scoring data, matching the performance and data coverage of each data source, and generating an adjusted weight data set;

[0037] Comprehensively refer to the weight settings in the weight adjustment data set and the scores and data distribution of multiple data sources to optimize the weight allocation and generate an optimized weight configuration set;

[0038] Based on the optimized weight configuration set, the weight of each data source is calculated using the formula: ;

[0039] Determine the adjusted weight configuration;

[0040] in, is the adjusted weight configuration, Represents the data source The credit score adjustment weights, Is the data source 's rating.

[0041] As a further solution of the present invention, the steps for obtaining the collaborative law enforcement record are specifically as follows:

[0042] Extracting weight parameters of each data source from the adjusted weight configuration, performing weighted fusion in combination with input data from multiple data sources, strengthening the influence of key data sources through weights, and generating a preliminary weighted fusion data set;

[0043] Verifying the fields in the preliminary weighted fusion data set, eliminating data errors and incomplete entries, and generating a data set that has undergone field verification;

[0044] Analyze the data set that has undergone field verification, use dynamic weights to eliminate interference from non-key fields, retain core data by comparing data weights and actual performance, and generate a key data field set;

[0045] The key data field set is compiled and integrated, and data integration technology is applied, combining the weight and data value of each field, using the formula: ;

[0046] The output is a collaborative law enforcement record;

[0047] in, Indicates collaborative law enforcement records, is the adjusted weight, reflecting the data source The influence of It is a key data field that has been strictly screened.

[0048] A method for generating law enforcement records by fusion of multi-source data, the method for generating law enforcement records by fusion of multi-source data is performed based on the above-mentioned law enforcement record generation system by fusion of multi-source data, and comprises the following steps:

[0049] S1: Collect raw data from multiple data sources, clean and unify the format, compare identifiers for each record, remove duplicates, extract and merge related fields from multiple data sets through field linking, and generate integrated raw records;

[0050] S2: Based on the integrated original records, perform data validity verification, check the range and type of each field, use deviation identification to calculate and exclude outliers, restructure the remaining data, and generate a cleaned data set;

[0051] S3: Using the cleaned data set, perform statistical analysis to evaluate the contribution and consistency of multiple data sources, use coverage assessment to evaluate data integrity, use weighted calculation method to integrate multiple indicator scores, and establish a data source trust score table;

[0052] S4: According to the scores in the data source trust score table, the weight distribution of the input data is adjusted, the weight is updated through dynamic weight configuration, and the weight is redistributed according to the current characteristics and reliability of the data source to obtain the adjusted weight configuration;

[0053] S5: According to the adjusted weight configuration, a weighted synthesis algorithm is used to fuse the information of multiple data sources, and integrity and consistency checks are performed to eliminate interference from minor fields, and generate a preliminary fusion result;

[0054] S6: Based on the preliminary fusion results, through standardized processing and verification processes, verify whether the data meets the law enforcement record generation specifications, form a structured record, and generate a collaborative law enforcement record.

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

[0056] In the present invention, data quality is further ensured by checking the data value range and calculating the deviation value, and the reliability of the data set is enhanced by removing abnormal data. The quality assessment of the data source and the fairness of the input are ensured through quantitative scoring and dynamic weight adjustment, making the law enforcement records generated in the end more comprehensive and authoritative. This refined data processing not only improves the accuracy of law enforcement records, but also strengthens the security and integrity of information, thereby significantly improving the response speed and decision-making quality of law enforcement agencies. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is a system flow chart of the present invention;

[0058] Figure 2 A flow chart of the acquisition steps for integrating original records for the present invention;

[0059] Figure 3 A flow chart of the steps for obtaining the processed data set of the present invention;

[0060] Figure 4 A flowchart of the steps for obtaining the information source trust score table of the present invention;

[0061] Figure 5A flow chart of the steps for obtaining the adjusted weight configuration of the present invention;

[0062] Figure 6 This is a flow chart of the steps for obtaining collaborative law enforcement records of the present invention. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with 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.

[0064] 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 indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0065] Embodiment 1:

[0066] See also Figure 1 The present invention provides a technical solution: a law enforcement record generation system for multi-source data fusion includes:

[0067] The data collection module obtains raw data from multiple data sources, normalizes the raw data, removes duplicate records after comparison, and extracts related data fields including law enforcement officer information, illegal behavior description, time and place, and evidence materials through rule matching to generate integrated raw records;

[0068] The anomaly detection module performs data value range verification on the integrated original records, calculates the deviation value of each data field according to the specified deviation range, marks and removes the entries whose deviation values ​​exceed the set standard, reconstructs the data table for the cleaned data, and generates a processed data set;

[0069] The source evaluation module quantitatively scores the numerical distribution, consistency, and evidence coverage of multiple data sources based on the processed data set, obtains the overall score result by performing weighted average processing on the score set, summarizes the overall score result by data source dimension and stores it as an independent record to establish a source trust score table;

[0070] The weight adjustment module dynamically adjusts the input weight distribution of multiple data sources according to the scoring data in the source trust scoring table, performs comparison according to the current characteristics of the input data, allocates weight parameters of multiple sources in combination with the scoring and data distribution, and obtains the adjusted weight configuration;

[0071] The data fusion and generation module performs weighted fusion on the input data of each data source based on the adjusted weight configuration, performs field verification on the fusion results, eliminates the interference of non-critical data fields on the results based on the weights, and outputs the fields that meet the fusion rules as collaborative law enforcement records.

[0072] The integrated original records include normalized data, deduplicated records, and extracted related fields. The processed data set includes verified data entries, cleaned data with abnormal items removed, and reconstructed data tables. The source trust score table includes the source score, coverage data, and consistency score. The adjusted weight configuration includes the source weight parameters, score weighting parameters, and distribution weight parameters. The collaborative law enforcement records include weighted fusion data, verified valid fields, and output fields that comply with the rules.

[0073] See also Figure 2 , the steps to obtain the integrated original records are as follows:

[0074] After extracting data from multiple data sources, the data is standardized to eliminate the dimension effect and generate a standardized data set;

[0075] After extracting data from multiple data sources, standardization is performed to eliminate the impact of dimensions. This step is the basis of data processing. The standardized data set is the result of the processing. This process is carried out by converting the data into a form with a common format and proportion to facilitate more efficient data comparison and analysis in subsequent steps. In addition, standardization is a commonly used technique in data analysis to improve data quality and comparability. This method is common in big data processing and statistical analysis. The purpose is to prepare a data set with uniform quality to support data operations and decision analysis.

[0076] Perform uniqueness verification on the standardized data set, compare the data through hash functions, identify and delete duplicate entries, and obtain a deduplicated data set;

[0077] The data is compared through the hash function to identify and delete duplicate entries. This process is a key step in data cleaning. The deduplication data set is generated by this. The use of hash functions can effectively identify duplicate records in batch data sets. This technology is particularly critical in the fields of database management and information security. By generating a unique hash value for each piece of data for rapid comparison, the uniqueness and integrity of the data set are ensured. This step can greatly reduce the complexity of data processing and improve data processing speed.

[0078] Use data matching technology to identify and extract key fields in the deduplicated data set, including user ID and transaction date, and build a related field data set based on the fields;

[0079] Identify and extract key fields in the deduplicated data set, including user ID and transaction date, and build an associated field data set. This process involves matching algorithms and data extraction technology, allowing key information to be quickly extracted from batches of data to provide support for data analysis and business decisions. The associated field data set increases the commercial value and operability of the data by accurately identifying and associating key information in the data. This is the basis for building an effective data model and is crucial for data mining and analysis.

[0080] Based on the associated field data set, data association analysis is performed and the association degree calculation formula is applied: ;

[0081] Calculate and analyze the correlation between differentiated data fields to generate integrated original records;

[0082] in, Representative The value of a data field is used to represent the value of the field in the data set. Representative The value of a data field is used to represent the value of another field in the data set. It is The weight coefficient of the field is adjusted The influence of each field in the correlation calculation, It is The weight coefficient of the field is adjusted The influence of each field in the correlation calculation, Is seeking The weight coefficient used in the square sum is used to adjust The contribution in the denominator, Indicates Field and The correlation index between fields is used to quantify the strength of the correlation between two fields;

[0083] formula: ;

[0084] The formula is beneficial in that it adjusts the correlation calculation according to the critical weighting of the differentiated fields, matches the needs of differentiated scenarios, and is suitable for the relationship evaluation between multiple variables in the data environment;

[0085] Detailed explanation of the formula and the process of formula calculation and derivation:

[0086] set up Weight ,calculate Weight adjustment value:

[0087] ;

[0088] calculate and Weight adjustment value:

[0089] ;

[0090] ;

[0091] Calculate the relevance index:

[0092] ;

[0093] The results show that the field and There was a low correlation between them, indicating that potential associations or weight parameter adjustments need to be investigated between these two variables.

[0094] See also Figure 3 , the steps to obtain the processed data set are as follows:

[0095] Perform data value range verification on the integrated original records, check the compliance of each data point based on the preset standards of each field, verify the compliance of the data, and generate a data set that meets the standards;

[0096] Perform data range verification on the integrated original records. First, ensure that each data point meets the preset safety standards and operating range. This step requires reviewing the data of each field one by one. The review process includes comparing the deviation of the data point with the preset standard. Standardization processing includes converting the data into a unified format and adjusting the data to a preset numerical range. The standardization function used in the adjustment process needs to be set according to the data type and intended use to ensure the accuracy and availability of the data. The generated data set will be used for subsequent analysis and processing tasks, ensuring the integrity and accuracy of the data processing process.

[0097] Based on the data set that meets the standards, calculate the deviation value of each data field, compare the deviation value with the set deviation range, and generate a deviation value analysis data set;

[0098] After completing the initial review of the data points, the next key step is to calculate the deviation value of each field. The deviation value is calculated by determining the difference between each data point and the field mean. This process involves not only arithmetic calculations, but also statistical analysis of the deviation values ​​to identify those data points that are outside the normal variation range. Statistical analysis assists in determining the standard deviation and coefficient of variation of the data. These statistical parameters are obtained through data collection and long-term monitoring to ensure the reliability and accuracy of the analysis results, thereby generating a deviation analysis data set.

[0099] Screen out all data entries in the deviation analysis data set whose deviation values ​​exceed the standard, mark the entries, and perform removal operations to obtain a corrected data set;

[0100] The data set that has undergone the deviation value analysis needs to be screened to exclude those data entries that deviate from the standard. The screening process includes marking the data points that are beyond the deviation range and performing removal operations based on these marks. The removal criteria are based on the statistical analysis results in the data set and the preset deviation threshold. This step ensures the consistency and data quality of the data set. The processed data set will be cleaner and accurately reflect the actual situation. The removal process is performed using automated scripts to improve processing efficiency and reduce human errors. The generated corrected data set provides a solid foundation for analysis and decision-making.

[0101] The corrected data set is processed using the formula: ;

[0102] Calculate the adjusted standardized score for each data point to generate a processed data set;

[0103] in, represents the value of the data point, is the mean value of the data field, is the standard deviation, Used to adjust the score sensitivity, Representative Data points for Adjusted standardized scores for each data field;

[0104] formula: ;

[0105] The formula is useful in that it provides a flexible way to adjust the relationship between a data point and its standard deviation by introducing an adjustment factor , the weight of data points can be adjusted according to the distribution characteristics of actual data, so as to identify and process outliers. This is especially useful when processing batch data sets, which can effectively optimize the data processing process and improve the accuracy and efficiency of data processing;

[0106] Detailed explanation of the formula and the process of formula calculation and derivation:

[0107] Set up a set of data , the average value , standard deviation , adjustment coefficient , calculate for each data point value:

[0108] 1. Yes , calculate the calculation ;

[0109] 2. Yes ,calculate ;

[0110] 3. Yes ,calculate ;

[0111] 4. Yes ,calculate ;

[0112] 5. Yes ,calculate ;

[0113] sum The values ​​are: ;

[0114] The results showed that the adjusted The distribution of values ​​is uniform and consistent with the expected statistical setting, indicating that the data has been properly standardized, which helps in the data analysis and decision-making process.

[0115] See also Figure 4 ,The specific steps for obtaining the source trust score table are:

[0116] Quantitatively score multiple data sources in the processed data set to capture value distribution, consistency, and data coverage, and generate a preliminary scoring result set based on multi-dimensional statistical indicators;

[0117] The processed data set is scored to quantify the numerical distribution and consistency of multiple data sources and calculate the coverage of each data source. In addition, the data sources are weighted according to their quality and quantity to ensure the accuracy and fairness of the scoring. This process involves data processing and analysis technology. Each data source must undergo strict data quality review and statistical analysis to ensure the reliability of the scoring results and ensure that the data coverage is multidimensional. The scoring results of these data sources will directly affect the weighted average processing in subsequent steps.

[0118] By taking a weighted average of multiple scores in the preliminary scoring result set, each data source score is assigned a differentiated weight based on its data quality and quantity, and a weighted scoring data set is calculated and generated;

[0119] By analyzing the preliminary scoring results, a weighted average score is calculated. This requires that each data source be weighted according to its criticality and contribution. These weight parameters are determined by the data coverage and data quality. The data source score is reflected through a weighted average calculation. These calculations involve multiple statistical methods, including variance analysis and covariance calculation, to ensure that the scores of multiple data sources not only reflect the actual situation of the data source, but also maintain the overall consistency and balance of the scoring system.

[0120] Summarize the weighted scoring data set by data source dimension, aggregate the scoring results of each data source, ensure that the score of the data source can reflect the criticality of the contribution, and obtain the data source summary scoring set;

[0121] Aggregate the scoring results of multiple data sources and summarize them by data source dimension to ensure that the score of each data source can reflect its relative criticality in the entire data set. This aggregation process needs to refer to the relationship and influence between data sources and adopt advanced statistical techniques and data integration methods. These methods must be able to handle batch data sets to ensure the efficiency and accuracy of data processing, so as to create a comprehensive score for each data source. This score result will be used to establish the subsequent trust score table.

[0122] Score sets are aggregated based on data sources using the formula: ;

[0123] Calculate the normalized trust of each data source and establish a source trust score table ;

[0124] in, Indicates The ratings of the data sources, According to the data source The weight coefficient is determined by the quality and coverage of the

[0125] formula: ;

[0126] The benefit of the formula is that, by introducing weight coefficients and square roots, the ability to handle extreme values ​​is enhanced, ensuring the robustness and flexibility of the scoring system. At the same time, by processing absolute values, the impact of negative scores is eliminated, making the source trust score more fair and reliable.

[0127] Detailed explanation of the formula and the process of formula calculation and derivation:

[0128] Set the score with three data sources as , the corresponding weight is , the calculation process is as follows:

[0129] 1. Calculate the absolute sum of the weighted scores:

[0130] ;

[0131] 2. Calculate the weight and:

[0132] ;

[0133] 3. Apply the formula to calculate the source trust score:

[0134] ;

[0135] The results show that after comprehensively referring to the quality and contribution of multiple data sources, a source trust score of 9.1 was obtained, which indicates that the overall quality of the data source is high and provides reliable data support for subsequent decision-making and analysis.

[0136] See also Figure 5 , the specific steps for obtaining the adjusted weight configuration are:

[0137] Extract the score data of each data source from the source trust score table, analyze the value distribution and consistency, preliminarily determine the weight of each data source based on the data characteristics, and generate a preliminary weight distribution data set;

[0138] Analyze the scoring data in the source trust score table to identify the scoring characteristics and variability of each data source. This process determines the consistency of the data by counting the score fluctuations of each data source at different time points and using standard deviation and coefficient of variation calculations. These statistics help reveal the stability and reliability of the data source. The statistical analysis results of the scoring data are calculated based on the previous scoring records of each data source, including the average score, the highest score, the lowest score, and the score volatility. The results of these data statistics will directly affect the allocation of preliminary weights and provide a quantitative basis for the next step of weight adjustment.

[0139] Refine the initial weight allocation data set, compare the current input characteristics of each data source with the scoring data, dynamically adjust the weights, match the performance and data coverage of each data source, and generate an adjusted weight data set;

[0140] The weights are adjusted dynamically based on the current input characteristics of each data source and the preliminary weight analysis data set. This adjustment is based on the current input characteristics of the data source and the previous scoring data, capturing whether there are significant changes in the data source's recent performance, including the integrity, error rate, update frequency, and timeliness of the input data. These characteristics are acquired in real time through the data monitoring system, and the scoring data and weight analysis are calculated using previous data stored in the data management system to derive a weight adjustment plan for each data source and generate an adjusted weight data set, which will provide a basis for optimizing the weight configuration.

[0141] Comprehensively refer to the weight settings in the weight adjustment data set and the scores and data distribution of multiple data sources to optimize the weight allocation and generate an optimized weight configuration set;

[0142] The weight settings in the weight adjustment data set are comprehensively referenced with the scores of multiple data sources and their data distribution to optimize the weight distribution. The optimization process is carried out by comparing the scores of multiple data sources and the degree of match between their data input characteristics. In this process, special attention is paid to those data sources that show significant improvement or decline to ensure that the weight distribution is more accurate and reasonable. The optimized weight parameter set is obtained through data analysis and processing steps, including data normalization, weight standardization and weight restriction, to ensure that the optimized weights can reflect the real contribution of the data source and comply with the overall data processing strategy.

[0143] Based on the optimized weight configuration set, the weight of each data source is calculated using the formula: ;

[0144] Determine the adjusted weight configuration;

[0145] in, is the adjusted weight configuration, Represents the data source The credit score adjustment weights, Is the data source Ratings;

[0146] formula: ;

[0147] The benefit of the formula is that by introducing square root and absolute value processing, the weight of high-credit data sources is increased, while the impact of low-credit data sources is smoothed. In this way, the formula optimizes the weight distribution, making the contribution of data sources more fair and reflected;

[0148] Detailed explanation of the formula and the process of formula calculation and derivation:

[0149] There are three data sources set up, and the scores are , , , and the corresponding weight factors are set to , , The calculation process is as follows:

[0150] 1. Calculate the square root of the weighted score for each data source:

[0151] ;

[0152] ;

[0153] ;

[0154] 2. Calculate the total sum of square roots:

[0155] ;

[0156] 3. Calculate the weighted average weight configuration:

[0157] ;

[0158] The results show that by dynamically adjusting the weight configuration, data sources can be assigned matching weights based on their performance and credibility, ensuring the accuracy and matching of data processing.

[0159] See also Figure 6 , the specific steps for obtaining collaborative law enforcement records are:

[0160] Extract the weight parameters of each data source from the adjusted weight configuration, perform weighted fusion by combining the input data of multiple data sources, strengthen the influence of key data sources through weights, and generate a preliminary weighted fusion data set;

[0161] On the basis of adjusting the weights, the inputs of multiple data sources are integrated, and the credit scores and data quality of each data source are comprehensively referred to. The consistency and integrity of the data are ensured through algorithms, thereby improving the quality and efficiency of data fusion. These data are verified through a strict process to ensure that the data in each field meets the preset quality standards. This series of processing provides a solid foundation for data application and decision-making.

[0162] Verify the fields in the preliminary weighted fusion dataset, eliminate data errors and incomplete entries, and generate a dataset that has been verified by the fields;

[0163] Through the data verification procedure, inconsistencies and erroneous entries in the data set are identified and eliminated. This process involves a variety of data verification technologies, including data integrity checks, field validity verification, and standardization of data formats. Each step is strictly performed in accordance with the best practices of data management, ensuring the accuracy of the data processing process and the high quality of the data set, providing a reliable input source for subsequent data analysis and application.

[0164] Analyze the data set that has been verified by fields, use dynamic weights to eliminate interference from non-key fields, retain core data by comparing data weights with actual performance, and generate a set of key data fields;

[0165] On the basis of removing non-critical data fields, key data are analyzed and optimized. Data screening and weight adjustment ensure that only the most critical data are retained and utilized. This not only improves the efficiency of data processing, but also enhances the relevance and practicality of data analysis results. The generated key data sets provide a solid basis for formulating effective strategies and decisions.

[0166] Compile and integrate the key data field sets, apply data integration technology, combine the weight and data value of each field, and use the formula: ;

[0167] The output is a collaborative law enforcement record;

[0168] in, Indicates collaborative law enforcement records, is the adjusted weight, reflecting the data source The influence of It is a key data field that has been strictly screened;

[0169] formula: ;

[0170] The benefit of the formula is that by introducing weights and data fields The square root processing enhances the ability to process batches and data sources with significant differences, ensuring that the contribution of each data source in the weighted fusion process is correctly reflected according to its criticality. At the same time, the square root is used to reduce the impact of extreme values, thereby improving the stability and reliability of the results.

[0171] Detailed explanation of the formula and the process of formula calculation and derivation:

[0172] There are three data sources, and their weights are , the corresponding data field values ​​are . First, calculate the product of the square root value and weight of each data source:

[0173] ;

[0174] ;

[0175] ;

[0176] Then calculate the square root sum of the weights:

[0177] ;

[0178] Finally, substitute the formula to calculate the comprehensive score of the collaborative law enforcement record:

[0179] ;

[0180] The results show that the collaborative law enforcement record score is 7.01, which means that after weighting and square root processing, the contributions of multiple data sources are reasonably evaluated and integrated, ensuring the comprehensive utilization of data and the effectiveness of practical applications.

[0181] A method for generating law enforcement records by fusion of multi-source data, which is based on the above-mentioned law enforcement record generation system by fusion of multi-source data, and includes the following steps:

[0182] S1: Collect raw data from multiple data sources, clean and unify the format, compare identifiers for each record, remove duplicates, extract and merge related fields from multiple data sets through field linking, and generate integrated raw records;

[0183] S2: Based on the integration of original records, perform data validity verification, check the range and type of each field, use deviation identification to calculate and exclude outliers, restructure the remaining data, and generate a cleaned data set;

[0184] S3: Use the cleaned data set to perform statistical analysis, evaluate the contribution and consistency of multiple data sources, use coverage assessment to evaluate data integrity, use weighted calculation method to integrate multiple indicator scores, and establish a data source trust score table;

[0185] S4: According to the scores in the data source trust score table, the weight distribution of the input data is adjusted, and the weight is updated through dynamic weight configuration, which is redistributed according to the current characteristics and reliability of the data source to obtain the adjusted weight configuration;

[0186] S5: Based on the adjusted weight configuration, a weighted synthesis algorithm is used to fuse information from multiple data sources, and integrity and consistency checks are performed to eliminate interference from minor fields and generate preliminary fusion results;

[0187] S6: Based on the preliminary fusion results, verify whether the data meets the law enforcement record generation specifications through standardized processing and verification processes, form structured records, and generate collaborative law enforcement records.

[0188] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A law enforcement record generation system based on multi-source data fusion, characterized in that: The system comprises: The data collection module obtains raw data from multiple data sources, normalizes the raw data, removes duplicate records after comparison, and extracts related data fields including law enforcement personnel information, illegal behavior descriptions, time and place, and evidence materials through rule matching to generate integrated raw records; The anomaly detection module performs a data value range check on the integrated original records, calculates the deviation value of each data field according to the specified deviation range, marks and removes entries whose deviation values ​​exceed the set standard, reconstructs the data table for the cleaned data, and generates a processed data set; The source evaluation module quantitatively scores the numerical distribution, consistency and evidence material coverage of multiple data sources based on the processed data set, obtains an overall scoring result by performing weighted average processing on the scoring set, summarizes the overall scoring result by data source dimension and stores it as an independent record, and establishes a source trust scoring table; The weight adjustment module dynamically adjusts the input weight distribution of multiple data sources according to the score data in the source trust score table, performs comparison according to the current characteristics of the input data, allocates weight parameters of multiple sources in combination with the score and data distribution, and obtains the adjusted weight configuration; The data fusion and generation module performs weighted fusion on the input data of each data source based on the adjusted weight configuration, performs field verification on the fusion result, excludes interference of non-critical data fields on the result based on the weight, and outputs the fields that meet the fusion rules as collaborative law enforcement records; The specific steps for obtaining the collaborative law enforcement records are as follows: Extracting weight parameters of each data source from the adjusted weight configuration, performing weighted fusion in combination with input data from multiple data sources, strengthening the influence of key data sources through weights, and generating a preliminary weighted fusion data set; Verifying the fields in the preliminary weighted fusion data set, eliminating data errors and incomplete entries, and generating a data set that has undergone field verification; Analyze the data set that has undergone field verification, use dynamic weights to eliminate interference from non-key fields, retain core data by comparing data weights and actual performance, and generate a key data field set; The key data field set is compiled and integrated, and data integration technology is applied, combining the weight and data value of each field, using the formula: ； The output is a collaborative law enforcement record; in, Indicates collaborative law enforcement records, is the adjusted weight, reflecting the data source The influence of It is a key data field that has been strictly screened.

2. The law enforcement record generation system based on multi-source data fusion according to claim 1 is characterized in that: The integrated original records include normalized data, deduplicated records, and extracted related fields; the processed data set includes verified data entries, cleaned data with abnormal items removed, and reconstructed data tables; the source trust score table includes source score, coverage data, and consistency score; the adjusted weight configuration includes source weight parameters, score weighting parameters, and distribution weight parameters; the collaborative law enforcement records include weighted fusion data, verified valid fields, and output fields that comply with the rules.

3. The law enforcement record generation system based on multi-source data fusion according to claim 2 is characterized in that: The steps of obtaining the integrated original records are specifically as follows: After extracting data from multiple data sources, the data is standardized to eliminate the dimension effect and generate a standardized data set; Performing uniqueness verification on the standardized data set, comparing the data using a hash function, identifying and deleting duplicate entries, and obtaining a deduplicated data set; Using data matching technology, identifying and extracting key fields in the deduplicated data set, including user ID and transaction date, and constructing a related field data set based on the fields; Based on the associated field data set, data association analysis is performed and the association degree calculation formula is applied: ； Calculate and analyze the correlation between differentiated data fields to generate integrated original records; in, Representative The value of a data field is used to represent the value of the field in the data set. Representative The value of a data field is used to represent the value of another field in the data set. It is The weight coefficient of the field is adjusted The influence of each field in the correlation calculation, It is The weight coefficient of the field is adjusted The influence of each field in the correlation calculation, Is seeking The weight coefficient used in the square sum is used to adjust The contribution in the denominator, Indicates Field and The correlation index between fields is used to quantify the strength of the correlation between two fields.

4. The law enforcement record generation system based on multi-source data fusion according to claim 3 is characterized in that: The steps for obtaining the processed data set are specifically as follows: Performing data value range verification on the integrated original records, checking the compliance of each data point based on the preset standards of each field, verifying the compliance of the data, and generating a data set that meets the standards; Based on the data set that meets the standard, calculating the deviation value of each data field, comparing the deviation value with the set deviation range, and generating a deviation value analysis data set; Screening all data entries in the deviation analysis data set whose deviation values ​​exceed the standard, marking the entries, and performing a removal operation to obtain a corrected data set; The modified data set is processed using the formula: ； Calculate the adjusted standardized score for each data point to generate a processed data set; in, represents the value of the data point, is the mean value of the data field, is the standard deviation, Used to adjust the score sensitivity, Representative Data points for Adjusted normalized scores for each data field.

5. The law enforcement record generation system based on multi-source data fusion according to claim 4 is characterized in that: The steps for obtaining the source trust score table are specifically as follows: Quantitatively scoring multiple data sources in the processed data set to capture value distribution, consistency, and data coverage, and generating a preliminary scoring result set based on multi-dimensional statistical indicators; By performing weighted averaging processing on multiple scores in the preliminary scoring result set, each data source score is assigned a differentiated weight according to its data quality and quantity, and a weighted scoring data set is calculated and generated; Summarize the weighted scoring data set according to the data source dimension, aggregate the scoring results of each data source, ensure that the score of the data source can reflect the criticality of the contribution, and obtain a data source summary scoring set; Aggregate the score set based on the data source, using the formula: ； Calculate the normalized trust of each data source and establish a source trust score table ; in, Indicates The ratings of the data sources, According to the data source The weighting factor is determined by the quality and coverage of the 6. The law enforcement record generation system based on multi-source data fusion according to claim 5 is characterized in that: The steps for obtaining the adjusted weight configuration are specifically as follows: Extracting the score data of each data source from the source trust score table, analyzing the value distribution and consistency, preliminarily determining the weight of each data source based on the data characteristics, and generating a preliminary weight distribution data set; Refining the preliminary weight allocation data set, dynamically adjusting the weights according to the current input characteristics of each data source and the scoring data, matching the performance and data coverage of each data source, and generating an adjusted weight data set; Comprehensively refer to the weight settings in the weight adjustment data set and the scores and data distribution of multiple data sources to optimize the weight allocation and generate an optimized weight configuration set; Based on the optimized weight configuration set, the weight of each data source is calculated using the formula: ； Determine the adjusted weight configuration; in, is the adjusted weight configuration, Represents the data source The credit score adjustment weights, Is the data source 's rating.

7. A method for generating law enforcement records by fusion of multi-source data, characterized in that: The law enforcement record generation system based on multi-source data fusion according to any one of claims 1 to 6 is implemented, comprising the following steps: Collect raw data from multiple data sources, clean and unify the format, compare identifiers for each record, remove duplicates, extract and merge related fields from multiple data sets through field linking, and generate integrated raw records; Based on the integrated original records, perform data validity verification, check the range and type of each field, use deviation identification to calculate and exclude outliers, restructure the remaining data, and generate a cleaned data set; Using the cleaned data set, statistical analysis is performed to evaluate the contribution and consistency of multiple data sources, data integrity is evaluated using coverage assessment, and multiple indicator scores are integrated using a weighted calculation method to establish a data source trust score table; According to the scores in the data source trust score table, the weight distribution of the input data is adjusted, the weight is updated through dynamic weight configuration, and the weight is redistributed according to the current characteristics and reliability of the data source to obtain the adjusted weight configuration; According to the adjusted weight configuration, a weighted synthesis algorithm is used to fuse the information of multiple data sources, and integrity and consistency checks are performed to eliminate interference from minor fields, thereby generating a preliminary fusion result; Based on the preliminary fusion results, standardized processing and verification processes are used to verify whether the data meets the law enforcement record generation specifications, form structured records, and generate collaborative law enforcement records.

Images