A real-time transaction management system in the Metaverse Bank space

Abstract

The present invention discloses a real-time transaction management system in a metaverse bank space, which relates to the field of virtual space technology. The system uses a data acquisition module to collect virtual transaction data in real time, and cleans and formats these data through a data preprocessing unit to obtain a structured virtual transaction data set. The accuracy and integrity of the data are ensured, and the impact of data anomalies and missing data on system analysis is reduced. The feature extraction module extracts key features from the processed data set, providing basic information for subsequent data processing. The data processing module calculates the extracted feature set by constructing and applying a transaction algorithm model to obtain the virtual transaction density Dv, link jitter Jl and user behavior complexity Cu. The synergy of these modules enables the system to process transaction requests in real time and respond quickly to transaction activities, thereby significantly improving the transaction processing speed and system performance to meet the needs of high-frequency transactions.

Description

Technical Field

[0001] The present invention relates to the field of virtual space technology, and in particular to a real-time transaction management system within a metaverse bank space. Background Art

[0002] The real-time transaction management system in the Metaverse banking space belongs to the field of FinTech. Specifically, it is at the intersection of the virtual economy and blockchain technology. With the rise of the Metaverse concept, more and more financial institutions are beginning to explore financial transactions and management in the virtual world. The transaction management system in the Metaverse banking space is designed to achieve efficient and secure transaction processing in the virtual environment, ensuring that users can enjoy the same convenience and security as in the real world when conducting financial transactions in the virtual world.

[0003] At present, there are three main problems in the existing Metaverse Bank Space Management System: low virtual transaction density, severe link jitter, and high complexity of user behavior. These problems lead to low efficiency in system transaction processing, unstable network transmission, and poor user experience. Especially during peak trading periods, system performance will decline significantly, transaction delays will increase, and even transaction failures may occur. Existing systems often lack the ability to monitor in real time and optimize intelligently, making it difficult to quickly respond to and handle abnormal transactions. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a real-time transaction management system within the Metaverse Bank space, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: including a data acquisition module, a feature extraction module, a data processing module, a comprehensive security analysis module and an anomaly detection module;

[0006] The data acquisition module is used to connect to the Metaverse Bank space, collect virtual transaction data in real time, and pre-process the collected virtual transaction data to obtain a virtual transaction data set;

[0007] The feature extraction module is used to extract features from the preprocessed virtual transaction data set to obtain a transaction feature set;

[0008] The data processing module is used to construct a transaction algorithm model, and import the extracted transaction feature set into the transaction algorithm model to calculate and obtain the virtual transaction density Dv, link jitter Jl and user behavior complexity Cu;

[0009] The comprehensive security analysis module is used to summarize and calculate the results output by the transaction algorithm model to obtain the comprehensive performance index Ecc, and preset the performance threshold F1 to conduct preliminary comparative evaluation and analysis on whether the performance of the current bank space transaction system needs to be optimized;

[0010] The anomaly detection module is used to construct an abnormal transaction detection formula, calculate and obtain the abnormal transaction detection value Ad, and then perform a comprehensive calculation with the obtained comprehensive performance index Ecc to obtain the comprehensive optimization index Occ, and perform a secondary comparative evaluation of the preset optimization threshold Y to generate an iterative mechanism.

[0011] Preferably, the data acquisition module includes a data acquisition unit, a data preprocessing unit and a data storage unit;

[0012] The data collection module is used to create an API application program interface and integrate with the transaction system, network detection tools and bank space backend of the Metaverse Bank Space to collect virtual transaction data in real time. The virtual transaction data includes transaction logs, network fluctuation logs and user operation logs;

[0013] The data preprocessing unit is used to use the log analysis tool Logstash to parse the transaction logs, network fluctuation logs and user operation logs in the transaction data, obtain the structured data format of the transaction data, and extract the virtual transaction density data, link jitter data and user behavior complex data of the bank space in the transaction logs, network fluctuation logs and user operation logs, and remove outliers and missing values, and then convert the data of different dimensions to a unified scale, and summarize and obtain the virtual transaction data set;

[0014] The data storage unit is used to build a database, store virtual transaction data sets, query and analyze the stored data through Elasticsearch, generate statistical reports and behavior analysis, and use the Kibana tool to create a visual dashboard to display operation statistics, user behavior patterns and performance data.

[0015] Preferably, the feature extraction module is used to extract a virtual transaction data set from a database, perform feature extraction to obtain a transaction feature set, wherein the transaction feature set includes a virtual transaction density feature set, a link jitter feature set, and a user behavior complexity feature set, and analyze the virtual transaction data set to extract an abnormal transaction feature set;

[0016] The virtual transaction density feature set includes the transaction quantity Nt and the time window length T;

[0017] The link jitter feature set includes network transmission delay R and total transmission times M;

[0018] The user behavior complexity feature set includes operation frequency f, number of operation types P and total number of users U;

[0019] The abnormal transaction feature set includes abnormal transaction delay time T ano , total transaction delay time T tot , Number of abnormal transactions Q;

[0020] The abnormal transaction feature set uses the transaction log analysis tool ELKStack to parse each virtual transaction data record, identify and mark transactions with transaction delays significantly higher than normal levels as abnormal transactions, and extract the abnormal transaction delay time T of the abnormal transactions. ano , total transaction delay time T tot and the number of abnormal transactions Q.

[0021] Preferably, the data processing module includes a virtual transaction density processing unit, a link jitter processing unit and a user behavior complexity processing unit;

[0022] The virtual transaction density processing unit is used to construct a transaction density algorithm model, input the extracted virtual transaction density feature set into the transaction density algorithm model, and perform calculation and analysis to obtain the virtual transaction density Dv;

[0023] The virtual transaction density Dv is calculated and obtained by the following transaction density algorithm model:

[0024]

[0025] In the formula, t represents time, and Nt represents the number of transactions within time t.

[0026] Preferably, the link jitter processing unit is used to construct a link jitter algorithm model, and input the extracted link jitter feature set into the link jitter algorithm model to perform calculation and analysis to obtain the link jitter J1;

[0027] The link jitter J1 is calculated and obtained by the following link jitter algorithm model:

[0028]

[0029] In the formula, Ri represents the delay of the i-th network transmission, Indicates the average value of network transmission delay.

[0030] Preferably, the user behavior complexity processing unit is used to construct a user behavior complexity processing model, load the extracted user behavior complexity feature set into the user behavior complexity processing model, and perform calculation and analysis to obtain the user behavior complexity Cu;

[0031] The user behavior complexity Cu is calculated and obtained by the following user behavior complexity processing model:

[0032]

[0033] In the formula, f jk represents the operation frequency f of the kth operation of user j, and log represents the logarithmic function;

[0034] Indicates the accumulation of all user j’s behaviors;

[0035] It means summing up all operation types k of each user j.

[0036] Preferably, the comprehensive safety analysis module includes a comprehensive calculation unit and a performance evaluation unit;

[0037] The comprehensive calculation unit is used to correlate and summarize the virtual transaction density Dv, link jitter Jl and user behavior complexity Cu output by the data processing module to obtain a comprehensive performance index Ecc;

[0038] The comprehensive performance index Ecc is calculated by the following algorithm formula:

[0039]

[0040] In the formula, α represents the inverse weight value of the virtual transaction density Dv, β represents the weight value of the link jitter Jl, and γ represents the weight value of the user behavior complexity Cu. The specific values ​​are set by the user, and α+β+γ=1.

[0041] Preferably, the performance evaluation unit is used to preset a performance threshold F1 based on the normal performance index of the Metaverse Bank space, and then conduct a preliminary comparative evaluation with the obtained comprehensive performance index Ecc to analyze the performance of the current Metaverse Bank space transaction environment;

[0042] The specific evaluation plan is as follows:

[0043] When the comprehensive performance index Ecc ≥ performance threshold F1, it indicates that the performance of the current Metaverse bank space transaction environment is abnormal. At this time, the optimization control strategy is activated. The optimization control strategy includes sending instructions to the load balancer to balance the server load of the bank space, optimize the concurrent processing capacity of the system, analyze the existing network topology, identify the network optimization space, re-plan the network structure, and introduce an intelligent assistant to simplify user operations;

[0044] When the comprehensive performance indicator Ecc is less than the performance threshold F1, it means that the performance of the current Metaverse Bank space transaction environment is normal.

[0045] Preferably, the anomaly detection module includes an anomaly detection analysis unit, a comprehensive optimization calculation unit and an optimization evaluation unit;

[0046] The anomaly detection and analysis unit is used to analyze the performance anomalies of the current Metaverse Bank space transaction environment and optimize it, then load the acquired abnormal transaction feature set into calculation to obtain the abnormal transaction detection value Ad, and analyze which transactions are abnormal in terms of delay and weight;

[0047] The abnormal transaction detection value Ad is calculated by the following algorithm formula:

[0048]

[0049] Where, T anon represents the delay time of the nth abnormal transaction, W n Indicates the preset weight value of the nth abnormal transaction, W tot Indicates the preset weight value of total transactions;

[0050] The comprehensive optimization calculation unit is used to calculate and associate the acquired abnormal transaction detection value Ad with the acquired comprehensive performance index Ecc to obtain the comprehensive optimization index Occ;

[0051] The comprehensive optimization index Occ is calculated by the following algorithm formula:

[0052] Qcc=(Ad*a1)+(Ecc*a2)+A;

[0053] Wherein, a1 and a2 represent the preset weight values ​​of the abnormal transaction detection value Ad and the obtained comprehensive performance index Ecc, respectively, which are used to adjust the influence of the comprehensive evaluation value and the abnormal transaction detection value on the optimization result. The specific parameters are set by the user, and A represents the correction coefficient.

[0054] Preferably, the optimization evaluation unit performs a secondary comparative evaluation by comparing the preset optimization threshold value Y with the obtained comprehensive optimization index Occ by the user, analyzes and comprehensively evaluates the system performance and abnormal transaction conditions, and provides a basis for system optimization;

[0055] The specific evaluation plan is as follows:

[0056] When the comprehensive optimization index Occ>optimization threshold Y, it means that the system performance of the currently optimized Metaverse Bank space is abnormal. At this time, based on the current optimization control strategy, the optimization control strategy is executed again for iterative optimization.

[0057] When the comprehensive optimization index Occ≤optimization threshold Y, it means that the system performance of the currently optimized Metaverse Bank space is normal.

[0058] The present invention provides a real-time transaction management system in the Metaverse Bank space. It has the following beneficial effects:

[0059] (1) The system uses the data acquisition module to collect virtual transaction data from the Metaverse Bank space in real time, including transaction logs, network fluctuation logs, and user operation logs, and cleans and formats these data through the data preprocessing unit to obtain a structured virtual transaction data set. This process ensures the accuracy and integrity of the data and reduces the impact of data anomalies and missing data on system analysis. The feature extraction module extracts key features from the processed data set, such as virtual transaction density, link jitter, and user behavior complexity, providing basic information for subsequent data processing. The data processing module calculates the extracted feature set by constructing and applying a transaction algorithm model to obtain the virtual transaction density Dv, link jitter Jl, and user behavior complexity Cu. The synergy of these modules enables the system to process transaction requests in real time and respond quickly to transaction activities, thereby significantly improving transaction processing speed and system performance to meet the needs of high-frequency trading.

[0060] (2) The system plays a key role in improving the security and stability of the system through the comprehensive security analysis module and anomaly detection module of the transaction management system. The comprehensive security analysis module generates a comprehensive performance index Ecc by summarizing and calculating the virtual transaction density Dv, link jitter Jl and user behavior complexity Cu. This index is compared with the preset performance threshold F1 to evaluate the current performance status of the system. When the comprehensive performance index Ecc exceeds the performance threshold F1, the system will start the optimization control strategy to adjust and optimize the system settings. The anomaly detection module analyzes the abnormal transaction feature set, calculates the abnormal transaction detection value Ad, and generates a comprehensive optimization index Occ in combination with the comprehensive performance index Ecc for further optimization evaluation. When transaction delays or weight anomalies are found, the system can promptly identify potential security risks and take necessary measures. This mechanism effectively prevents the risks caused by system anomalies or security vulnerabilities and enhances the overall security and stability of the system.

[0061] (3) The system combines the abnormal transaction detection value Ad with the comprehensive performance index Ecc through the comprehensive optimization calculation unit to generate the comprehensive optimization index Occ. This formula is compared and evaluated twice with the preset optimization threshold Y to determine the optimization effect of the system. When the comprehensive optimization index Occ exceeds the optimization threshold Y, the system will execute the optimization strategy again, such as adjusting load balancing, optimizing network structure, and simplifying user operation processes. This iterative optimization mechanism ensures that the system can make timely adjustments when facing performance bottlenecks, improve processing capabilities and stability, and thus reduce transaction delays and failures. Through these optimization measures, users' transaction experience in the Metaverse Bank space will become smoother and more efficient, improve user satisfaction, and enhance the market competitiveness of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is a flow chart of a real-time transaction management system within a Metaverse bank space according to the present invention. DETAILED DESCRIPTION

[0063] 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] Example 1

[0065] See also Figure 1 , the present invention provides a real-time transaction management system in the Metaverse Bank space. To achieve the above purpose, the present invention is implemented through the following technical solutions: including a data acquisition module, a feature extraction module, a data processing module, a comprehensive security analysis module and an anomaly detection module;

[0066] The data collection module is used to connect to the Metaverse Bank space, collect virtual transaction data in real time, and pre-process the collected virtual transaction data to obtain a virtual transaction data set;

[0067] The feature extraction module is used to extract features from the preprocessed virtual transaction data set to obtain a transaction feature set;

[0068] The data processing module is used to build a transaction algorithm model, and import the extracted transaction feature set into the transaction algorithm model to calculate and obtain the virtual transaction density Dv, link jitter Jl and user behavior complexity Cu;

[0069] The comprehensive security analysis module is used to summarize and calculate the results output by the transaction algorithm model to obtain the comprehensive performance index Ecc, and preset the performance threshold F1 to conduct preliminary comparative evaluation and analysis to determine whether the performance of the current bank space transaction system needs to be optimized;

[0070] The anomaly detection module is used to construct an abnormal transaction detection formula, calculate and obtain the abnormal transaction detection value Ad, and then perform a comprehensive calculation with the obtained comprehensive performance index Ecc to obtain the comprehensive optimization index Occ, and perform a secondary comparative evaluation of the preset optimization threshold Y to generate an iterative mechanism.

[0071] In this embodiment, the system ensures real-time and comprehensive collection of virtual transaction data from the Metaverse Bank space through the data acquisition module, and obtains a structured virtual transaction data set through data preprocessing. This process effectively reduces the impact of data anomalies and missingness on subsequent analysis, allowing the system to perform efficient calculations based on accurate data. The feature extraction module further extracts key features from the preprocessed data set, constructs a comprehensive transaction feature set, and lays the foundation for the precise calculation of the data processing module. Through the cooperation of these modules, the system realizes the efficient collection and processing of virtual transaction data, providing solid data support for further analysis. In the data processing stage, the data processing module calculates the extracted transaction features by constructing a transaction algorithm model, and obtains the virtual transaction density Dv, link jitter Jl and user behavior complexity Cu. The calculation of these key indicators provides a data basis for the comprehensive security analysis of the system. The comprehensive security analysis module summarizes and calculates these indicators to generate a comprehensive performance indicator Ecc, and makes a preliminary comparison with the preset performance threshold F1 to evaluate whether the system performance meets the requirements. The optimization evaluation mechanism of this module can timely discover the shortcomings of system performance and start the corresponding optimization strategy, thereby improving the overall performance and stability of the system. The anomaly detection module further strengthens the monitoring capability of the system by calculating the abnormal transaction detection value Ad, and then performing a comprehensive calculation with the obtained comprehensive performance index Ecc to obtain the comprehensive optimization index Occ, and performing a secondary comparative evaluation with the preset optimization threshold Y to ensure that the system can identify and handle abnormal transactions in a timely manner. This iterative optimization mechanism enables the system to quickly adjust and optimize strategies when facing performance bottlenecks or abnormal transactions, significantly improving the real-time and accuracy of transactions.

[0072] Example 2

[0073] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the data acquisition module includes a data acquisition unit, a data preprocessing unit and a data storage unit;

[0074] The data collection module is used to create an API application program interface to integrate with the Metaverse Bank Space's transaction system, network detection tools, and bank space backend to collect virtual transaction data in real time. Virtual transaction data includes transaction logs, network fluctuation logs, and user operation logs.

[0075] The data preprocessing unit is used to use the log analysis tool Logstash to parse the transaction logs, network fluctuation logs and user operation logs in the transaction data, obtain the structured data format of the transaction data, and extract the virtual transaction density data, link jitter data and user behavior complex data of the bank space from the transaction logs, network fluctuation logs and user operation logs, and remove outliers and missing values, and then convert the data of different dimensions to a unified scale, and summarize to obtain the virtual transaction data set;

[0076] The data storage unit is used to build a database, store virtual transaction data sets, query and analyze the stored data through Elasticsearch, generate statistical reports and behavioral analysis, and use the Kibana tool to create a visual dashboard to display operation statistics, user behavior patterns, and performance data.

[0077] The feature extraction module is used to extract the virtual transaction data set in the database, perform feature extraction to obtain the transaction feature set, which includes the virtual transaction density feature set, link jitter feature set and user behavior complexity feature set, and analyze the virtual transaction data set to extract the abnormal transaction feature set;

[0078] The virtual transaction density feature set includes the number of transactions Nt and the time window length T;

[0079] The link jitter feature set includes network transmission delay R and total transmission times M;

[0080] The user behavior complexity feature set includes operation frequency f, number of operation types P, and total number of users U;

[0081] The abnormal transaction feature set includes abnormal transaction delay time T ano , total transaction delay time T tot , Number of abnormal transactions Q;

[0082] The abnormal transaction feature set uses the transaction log analysis tool ELKStack to parse each virtual transaction data record, identify and mark transactions with transaction delays significantly higher than normal levels as abnormal transactions, and extract the abnormal transaction delay time T of abnormal transactions. ano , total transaction delay time T tot and the number of abnormal transactions Q.

[0083] In this embodiment, the system realizes efficient connection with the Metaverse Bank Space Transaction System, network detection tools and bank space background through the integrated design of the data acquisition module, and collects virtual transaction data including transaction logs, network fluctuation logs and user operation logs in real time. The data preprocessing unit uses Logstash to parse and standardize the data, remove outliers and missing values, unify the scale of data of different dimensions, and lay a solid foundation for data storage and analysis. The data storage unit realizes efficient data storage, query and visualization by building a database and combining Elasticsearch and Kibana, ensuring the structured and visualized analysis of data, and providing a clear and comprehensive view for subsequent processing. The feature extraction module further extracts key features from the structured virtual transaction data set, including transaction feature sets including virtual transaction density feature sets, link jitter feature sets and user behavior complexity feature sets, and analyzes the virtual transaction data set, extracts abnormal transaction feature sets, and identifies and marks records with significant abnormal transaction delays. The function of this module optimizes the analysis of transaction data, provides a more accurate feature set, and provides detailed information for subsequent processing and analysis of the system.

[0084] Example 3

[0085] This embodiment is explained in Example 2. Please refer to Figure 1 ,Specifically: the data processing module includes a virtual transaction density ,processing unit, a link jitter processing unit and a user behavior complexity ,processing unit;

[0086] The virtual transaction density processing unit is used to construct a transaction density algorithm model, input the extracted virtual transaction density feature set into the transaction density algorithm model, and perform calculation and analysis to obtain the virtual transaction density Dv;

[0087] The virtual transaction density Dv is calculated by the following transaction density algorithm model:

[0088]

[0089] In the formula, t represents time, and Nt represents the number of transactions within time t.

[0090] The link jitter processing unit is used to construct a link jitter algorithm model, and input the extracted link jitter feature set into the link jitter algorithm model to perform calculation and analysis to obtain the link jitter J1;

[0091] The link jitter J1 is calculated and obtained by the following link jitter algorithm model:

[0092]

[0093] In the formula, Ri represents the delay of the i-th network transmission, Indicates the average value of network transmission delay.

[0094] The user behavior complexity processing unit is used to construct a user behavior complexity processing model, load the extracted user behavior complexity feature set into the user behavior complexity processing model, and perform calculation and analysis to obtain the user behavior complexity Cu;

[0095] The user behavior complexity Cu is calculated through the following user behavior complexity processing model:

[0096]

[0097] In the formula, f jk represents the operation frequency f of the kth operation of user j, and log represents the logarithmic function;

[0098] Indicates the accumulation of all user j’s behaviors;

[0099] It means summing up all operation types k of each user j.

[0100] In this embodiment, the data processing module in the system provides a comprehensive analysis of virtual transaction data through a virtual transaction density processing unit, a link jitter processing unit, and a user behavior complexity processing unit. The virtual transaction density processing unit constructs a transaction density algorithm model, calculates the virtual transaction density feature set, and obtains the virtual transaction density Dv. This indicator effectively measures the transaction volume density in a specific time period and reflects the intensity of the system load. The link jitter processing unit calculates the link jitter Jl through the link jitter algorithm model, quantifies the fluctuation of the network transmission delay, and provides an assessment of network stability. The user behavior complexity processing unit calculates the user behavior complexity Cu through the user behavior complexity processing model, evaluates the frequency and complexity of user operations, and helps understand the impact of user behavior on system performance.

[0101] Example 4

[0102] This embodiment is explained in Example 3, please refer to Figure 1 ,Specifically: the comprehensive safety analysis module includes a comprehensive ,computation unit and a performance evaluation unit;

[0103] The comprehensive calculation unit is used to correlate and summarize the virtual transaction density Dv, link jitter Jl and user behavior complexity Cu output by the data processing module to obtain a comprehensive performance index Ecc;

[0104] The comprehensive performance index Ecc is calculated by the following algorithm formula:

[0105]

[0106] In the formula, α represents the inverse weight value of the virtual transaction density Dv, β represents the weight value of the link jitter Jl, and γ represents the weight value of the user behavior complexity Cu. The specific values ​​are set by the user, and α+β+γ=1.

[0107] The performance evaluation unit is used to preset the performance threshold F1 based on the normal performance index of the Metaverse Bank space, and then conduct a preliminary comparative evaluation with the obtained comprehensive performance index Ecc to analyze the performance of the current Metaverse Bank space transaction environment;

[0108] The specific evaluation plan is as follows:

[0109] When the comprehensive performance indicator Ecc ≥ performance threshold F1, it indicates that the performance of the current Metaverse Bank Space transaction environment is abnormal. At this time, the optimization control strategy is activated. The optimization control strategy includes sending instructions to the load balancer to balance the server load of the bank space and optimize the concurrent processing capacity of the system. At the same time, it analyzes the existing network topology, identifies network optimization space, replans the network structure, and introduces an intelligent assistant to simplify user operations.

[0110] When the comprehensive performance indicator Ecc is less than the performance threshold F1, it indicates that the performance of the current Metaverse Bank space transaction environment is normal.

[0111] In this embodiment, the system summarizes the virtual transaction density Dv, link jitter Jl and user behavior complexity Cu into a comprehensive performance index Ecc through a comprehensive calculation unit. This process weights each index by setting a weight value to ensure the comprehensiveness and accuracy of the comprehensive performance index. The performance evaluation unit compares and evaluates the comprehensive performance index Ecc according to the preset performance threshold F1 to determine the performance status of the current system. By comparing with the performance threshold F1, the system can identify performance anomalies in a timely manner and start corresponding optimization control strategies, such as adjusting server load, optimizing network structure and introducing intelligent assistants. These optimization measures not only improve the concurrent processing capability of the system, but also improve the stability of the network and the convenience of user operation. When the comprehensive performance index Ecc is lower than the threshold A, the system can maintain normal operation and ensure continuous system stability. The improvement of this module effectively improves the overall performance and response speed of the system, enabling the Metaverse Bank space to maintain efficient and stable operation in a high-load and complex operating environment.

[0112] Example 5

[0113] This embodiment is explained in Example 4. Please refer to Figure 1 ,Specifically: the anomaly detection module includes an anomaly detection analysis unit, a ,comprehensive optimization calculation unit and an optimization evaluation unit;

[0114] The anomaly detection and analysis unit is used to analyze the performance anomalies of the current Metaverse Bank space transaction environment, optimize it, load the acquired abnormal transaction feature set, calculate and obtain the abnormal transaction detection value Ad, and analyze which transactions are abnormal in terms of delay and weight;

[0115] The abnormal transaction detection value Ad is calculated using the following algorithm formula:

[0116]

[0117] In the formula, represents the delay time of the nth abnormal transaction, W n Indicates the preset weight value of the nth abnormal transaction, W tot Indicates the preset weight value of total transactions;

[0118] The comprehensive optimization calculation unit is used to associate the acquired abnormal transaction detection value Ad with the acquired comprehensive performance index Ecc to obtain the comprehensive optimization index Occ;

[0119] The comprehensive optimization index Occ is calculated by the following algorithm formula:

[0120] Qcc=(Ad*a1)+(Ecc*a2)+A;

[0121] Wherein, a1 and a2 represent the preset weight values ​​of the abnormal transaction detection value Ad and the obtained comprehensive performance index Ecc, respectively, which are used to adjust the influence of the comprehensive evaluation value and the abnormal transaction detection value on the optimization result. The specific parameters are set by the user, and A represents the correction coefficient.

[0122] The optimization evaluation unit conducts a secondary comparative evaluation based on the user's preset optimization threshold value Y and the obtained comprehensive optimization index Occ, analyzes and comprehensively evaluates system performance and abnormal transactions, and provides a basis for system optimization;

[0123] The specific evaluation plan is as follows:

[0124] When the comprehensive optimization index Occ>optimization threshold Y, it means that the system performance of the currently optimized Metaverse Bank space is abnormal. At this time, based on the current optimization control strategy, the optimization control strategy is executed again for iterative optimization.

[0125] When the comprehensive optimization index Occ≤optimization threshold Y, it means that the system performance of the currently optimized Metaverse Bank space is normal.

[0126] In this embodiment, the system is responsible for calculating the abnormal transaction detection value Ad through the abnormal detection analysis unit, and analyzing which transactions show abnormalities based on the transaction delay time and the preset weight value. This process ensures that the situation where the transaction delay exceeds the normal range can be accurately identified, and marked according to the specific abnormality of the transaction. The comprehensive optimization calculation unit combines the abnormal transaction detection value Ad with the comprehensive performance index Ecc to calculate the comprehensive optimization index Occ, comprehensively considering the abnormal transactions and overall performance, and the optimization adjustment plan is more comprehensive and scientific. By calculating the abnormal transaction detection value Ad and the comprehensive optimization index Occ, the system can not only identify performance anomalies, but also accurately optimize specific problems. The optimization evaluation unit ensures the effectiveness of the optimization measures by performing a secondary comparison evaluation with the preset optimization threshold Y. If the comprehensive optimization index Occ exceeds the optimization threshold Y, the system will automatically execute further optimization measures to achieve iterative optimization. This mechanism enables the system to respond quickly and optimize and adjust when facing performance bottlenecks or abnormal transactions, improves the real-time and accuracy of transactions, and enhances the stability and reliability of the system. This intelligent anomaly detection and optimization mechanism enables the transaction environment of the Metaverse Bank space to maintain efficient operation under complex and high-load conditions, thereby improving the overall service quality and user experience.

[0127] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention.

Claims

1. A real-time transaction management system within the Metaverse Bank space, characterized by: It includes data acquisition module, feature extraction module, data processing module, comprehensive security analysis module and anomaly detection module; The data acquisition module is used to connect to the Metaverse Bank space, collect virtual transaction data in real time, and pre-process the collected virtual transaction data to obtain a virtual transaction data set; The feature extraction module is used to extract features from the preprocessed virtual transaction data set to obtain a transaction feature set; The feature extraction module is used to extract a virtual transaction data set from a database, perform feature extraction to obtain a transaction feature set, wherein the transaction feature set includes a virtual transaction density feature set, a link jitter feature set, and a user behavior complexity feature set, and analyze the virtual transaction data set to extract an abnormal transaction feature set; The virtual transaction density feature set includes the transaction quantity Nt and the time window length T; The link jitter feature set includes network transmission delay R and total transmission times M; The user behavior complexity feature set includes operation frequency f, number of operation types P and total number of users U; The abnormal transaction feature set includes abnormal transaction delay time T ano , total transaction delay time T tot , Number of abnormal transactions Q; The data processing module is used to construct a transaction algorithm model, and import the extracted transaction feature set into the transaction algorithm model to calculate and obtain the virtual transaction density Dv, link jitter Jl and user behavior complexity Cu; The data processing module includes a virtual transaction density processing unit, a link jitter processing unit and a user behavior complexity processing unit; The virtual transaction density processing unit is used to construct a transaction density algorithm model, input the extracted virtual transaction density feature set into the transaction density algorithm model, and perform calculation and analysis to obtain the virtual transaction density Dv; The virtual transaction density Dv is calculated and obtained by the following transaction density algorithm model: In the formula, t represents time, and Nt represents the number of transactions within time t; The link jitter processing unit is used to construct a link jitter algorithm model, and input the extracted link jitter feature set into the link jitter algorithm model to perform calculation and analysis to obtain the link jitter J1; The link jitter J1 is calculated and obtained by the following link jitter algorithm model: In the formula, Ri represents the delay of the i-th network transmission, Indicates the average value of network transmission delay; The user behavior complexity processing unit is used to construct a user behavior complexity processing model, load the extracted user behavior complexity feature set into the user behavior complexity processing model, and perform calculation and analysis to obtain the user behavior complexity Cu; The user behavior complexity Cu is calculated and obtained by the following user behavior complexity processing model: In the formula, f jk represents the k-th operation frequency f of user j, log represents the logarithmic function; The comprehensive security analysis module is used to summarize and calculate the results output by the transaction algorithm model to obtain the comprehensive performance index Ecc, and preset the performance threshold A to conduct preliminary comparative evaluation and analysis on whether the performance of the current bank space transaction system needs to be optimized; The comprehensive safety analysis module includes a comprehensive calculation unit and a performance evaluation unit; The comprehensive calculation unit is used to correlate and summarize the virtual transaction density Dv, link jitter Jl and user behavior complexity Cu output by the data processing module to obtain a comprehensive performance index Ecc; The comprehensive performance index Ecc is calculated by the following algorithm formula: In the formula, α represents the inverse weight value of the virtual transaction density Dv, β represents the weight value of the link jitter Jl, and γ represents the weight value of the user behavior complexity Cu. The specific value is set by the user, and α+β+γ=1; The anomaly detection module is used to construct an abnormal transaction detection formula, calculate and obtain the abnormal transaction detection value Ad, and then perform a comprehensive calculation with the obtained comprehensive performance index Ecc to obtain the comprehensive optimization index Occ, and perform a secondary comparative evaluation of the preset optimization threshold Y to generate an iterative mechanism; The anomaly detection module includes an anomaly detection analysis unit, a comprehensive optimization calculation unit and an optimization evaluation unit; The anomaly detection and analysis unit is used to analyze the performance anomaly of the current Metaverse Bank space transaction environment, optimize it, and then load the acquired abnormal transaction feature set into calculation to obtain the abnormal transaction detection value Ad; The abnormal transaction detection value Ad is calculated by the following algorithm formula: In the formula, represents the delay time of the nth abnormal transaction, W n Indicates the preset weight value of the nth abnormal transaction, W tot Indicates the preset weight value of total transactions; The comprehensive optimization calculation unit is used to calculate and associate the acquired abnormal transaction detection value Ad with the acquired comprehensive performance index Ecc to obtain the comprehensive optimization index Occ; The comprehensive optimization index Occ is calculated by the following algorithm formula: Occ=(Ad*a1)+(Ecc*a2)+Aa; Wherein, a1 and a2 represent the preset weight values ​​of the abnormal transaction detection value Ad and the obtained comprehensive performance index Ecc, respectively, and the specific parameters are set by the user, and Aa represents the correction coefficient.

2. A real-time transaction management system in a Metaverse bank space according to claim 1, characterized in that: The data acquisition module includes a data acquisition unit, a data preprocessing unit and a data storage unit; The data collection module is used to create an API application program interface and integrate with the transaction system, network detection tools and bank space backend of the Metaverse Bank Space to collect virtual transaction data in real time. The virtual transaction data includes transaction logs, network fluctuation logs and user operation logs; The data preprocessing unit is used to use the log analysis tool Logstash to parse the transaction logs, network fluctuation logs and user operation logs in the transaction data, obtain the structured data format of the transaction data, and extract the virtual transaction density data, link jitter data and user behavior complex data of the bank space in the transaction logs, network fluctuation logs and user operation logs, and remove outliers and missing values, and then convert the data of different dimensions to a unified scale, and summarize and obtain the virtual transaction data set; The data storage unit is used to build a database, store virtual transaction data sets, query and analyze the stored data through Elasticsearch, generate statistical reports and behavior analysis, and use the Kibana tool to create a visual dashboard to display operation statistics, user behavior patterns and performance data.

3. A real-time transaction management system in a Metaverse bank space according to claim 2, characterized in that: The performance evaluation unit is used to preset a performance threshold A based on the normal performance index of the Metaverse Bank space, and then conduct a preliminary comparative evaluation with the obtained comprehensive performance index Ecc to analyze the performance of the current Metaverse Bank space transaction environment; The specific evaluation plan is as follows: When the comprehensive performance index Ecc ≥ performance threshold A, it means that the performance of the current Metaverse Bank space transaction environment is abnormal, and the optimization control strategy is activated at this time; When the comprehensive performance indicator Ecc is less than the performance threshold A, it means that the performance of the current Metaverse Bank space transaction environment is normal.

4. A real-time transaction management system in a Metaverse bank space according to claim 3, characterized in that: The optimization evaluation unit performs a secondary comparative evaluation by using the preset optimization threshold Y of the user and the obtained comprehensive optimization index Occ to analyze the comprehensive evaluation system performance and abnormal transaction conditions; The specific evaluation plan is as follows: When the comprehensive optimization index Occ>optimization threshold Y, it means that the system performance of the currently optimized Metaverse Bank space is abnormal. At this time, based on the current optimization control strategy, the optimization control strategy is executed again for iterative optimization. When the comprehensive optimization index Occ≤optimization threshold Y, it means that the system performance of the currently optimized Metaverse Bank space is normal.

Images