A financial system monitoring system based on blockchain and cloud computing

Abstract

The present invention discloses a financial system monitoring system based on blockchain and cloud computing, belonging to the field of financial system monitoring technology. The system includes a data acquisition module, a data analysis module, a data processing module, a monitoring module, a prediction module, and a blockchain storage module; the output of the data acquisition module is connected to the input of the data analysis module, the monitoring module, and the blockchain storage module; the output of the data analysis module is connected to the input of the data processing module; the output of the data processing module is connected to the input of the monitoring module and the prediction module; and the output of the monitoring module is connected to the input of the blockchain storage module. The system can effectively prevent the occurrence of fraudulent transactions, coerced transactions, and other undesirable behaviors during financial transactions, and all data is uploaded to the blockchain storage module, further enhancing traceability and effectively preventing data loss.

Description

Technical Field

[0001] The present invention relates to the field of financial system monitoring technology, and in particular to a financial system monitoring system based on blockchain and cloud computing. Background Art

[0002] Cloud computing is an Internet-based computing method through which shared hardware and software resources and information can be provided to various computer terminals and other devices on demand, using the computer infrastructure provided by the service provider for computing and resources.

[0003] The financial system is a set of markets and intermediaries used by households, companies, and governments to implement their financial decisions. The financial system can provide a way for economic resources to be transferred across time, across borders, and between industries. It can also provide methods for managing risk, a way for clearing and payment settlement, and provide relevant mechanisms to reserve funds and purchase large, indivisible enterprises. Funds generally flow from those with surplus funds to those with shortages through the financial system.

[0004] In patent CN202011399131.3, an authorization signature system for a financial system based on the Internet of Things, an improved method for the local authorization mode is proposed, that is, after the front desk business operator initiates an authorization application to the auditor through the network at the teller terminal, the auditor needs to go to the operator who made the authorization request to authenticate the authorization signature and authorize the operator's business. After the authorization is completed, the operator completes the business processing on the teller terminal; this method is less efficient, especially when there are many front desk business operators. Auditors often need to go from one front desk to another to authorize, which increases the workload of auditors; at the same time, since the auditors authorize the signature on the teller terminal of the front desk business operator, there is a management risk in the process of imitating the auditor's handwriting instead of auditing; however, under such a signature method, there are still many problems, such as auditors maliciously modifying financial data, auditors being coerced to assist in illegal crimes, etc., and there are still certain uncontrollable risks. Therefore, this application proposes an adaptive learner mechanism that can comprehensively monitor the financial system. Summary of the Invention

[0005] The purpose of the present invention is to provide a financial system monitoring system based on blockchain and cloud computing to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] A financial system monitoring system based on blockchain and cloud computing, the system includes a data acquisition module, a data analysis module, a data processing module, a monitoring module, a prediction module, and a blockchain storage module;

[0008] The data acquisition module is used to obtain various financial transaction behavior data, including current financial transaction data, financial system transaction data in a secure state, and historical financial system transaction data of users. The data analysis module is used to perform cluster analysis on different financial transaction data and classify them according to different market styles and transaction objects. The data processing module is used to process financial transaction data to derive the user's potential preferred transaction methods. The monitoring module is used to retrieve current financial transactions and compare them with the user's potential preferred transaction methods, issue alarm messages for financial transactions that do not meet a certain similarity, and temporarily block transactions. The prediction module is used to predict the probability of success of the user's next transaction based on the user's transaction behavior data. The blockchain storage module is used to store financial transaction data and alarm data.

[0009] The output end of the data acquisition module is connected to the input end of the data analysis module, the monitoring module, and the blockchain storage module; the output end of the data analysis module is connected to the input end of the data processing module; the output end of the data processing module is connected to the input end of the monitoring module and the prediction module; the output end of the monitoring module is connected to the input end of the blockchain storage module.

[0010] According to the above technical solution, the data acquisition module includes a real-time data acquisition unit and a historical data acquisition unit;

[0011] The real-time data acquisition unit is used to acquire data on real-time financial transactions conducted by enterprise users; the historical data acquisition unit is used to acquire financial transaction data in a secure state and historical financial transaction data of enterprise users.

[0012] According to the above technical solution, the financial transaction data in a safe state refers to normal financial transaction data that is permitted by the state and has passed detection.

[0013] According to the above technical solution, the data analysis module includes a transaction object analysis unit and a market style analysis unit;

[0014] The transaction object analysis unit is used to analyze financial transaction data according to different transaction objects; the market style analysis unit is used to analyze financial transaction data according to different transaction markets.

[0015] According to the above technical solution, the transaction object analysis unit is divided into public transactions and private transactions according to different transaction objects;

[0016] The market style analysis unit is divided into currency trading, capital trading, foreign exchange trading, gold trading, and securities trading according to different trading markets.

[0017] According to the above technical solution, the data processing module includes a data receiving unit and a data processing unit;

[0018] The data receiving unit is used to receive the transmission data of the data acquisition module and the data analysis module; the data processing unit is used to process the data in the data receiving unit;

[0019] The output end of the data receiving unit is connected to the input end of the data processing unit.

[0020] According to the above technical solution, the processing process of the data processing unit is as follows:

[0021] S1. Obtain real-time financial system transaction content, recorded as Dataset A; obtain financial system transaction data in a secure state, recorded as Dataset B; obtain historical financial system transaction data of enterprise users, recorded as Dataset C;

[0022] S2. Perform cluster analysis on the transaction data in dataset A, clustering them into public transactions and private transactions based on the different types of transaction objects, and extract features from the transaction data using a neural network.

[0023] S3. Classify the trading products in the financial system transaction data in Dataset B according to different market styles and label them with style labels. In Dataset B, each financial transaction includes the geographical scope, business location, transaction nature, transaction object, financing method, and specific transaction tools. Each parameter has a corresponding text description.

[0024] S4. Analyze and process dataset C, learning the user's potential transaction preferences based on the enterprise user's historical financial system transaction data, and obtain positive feedback from the user's implicit feedback. Positive feedback includes transaction time less than X seconds and the number of failures in a single transaction less than Y times. The transaction data set in dataset C is denoted as M, where I represents any transaction data, and M+ represents the set of all financial system transaction data for which the enterprise user expresses positive feedback, and I∈M+. Any parameter in each financial system transaction data set in M+ is denoted as i, and i∈I.

[0025] A transaction time of less than X seconds indicates a high level of proficiency. Malicious or coerced transactions can create psychological pressure on traders, which can affect transaction speed. Replacement of a trader, leading to a lack of proficiency, can also affect transaction speed. A single transaction with fewer than Y failures indicates the authenticity of the trader. Failures in transactions are highly likely to indicate illegal activity. Therefore, transaction data that meets these two factors is considered positive feedback.

[0026] S5. Based on the transaction data I∈M+ in which the enterprise user has expressed positive feedback, define an enterprise user preference predictor to predict the user's preference for the financial transaction data parameter i, according to the formula:

[0027] P u，i =α+β u +ω u *λ i

[0028] Among them, P u，i represents the preference score of enterprise user u for transaction data parameter i; α represents the global offset, that is, the overall deviation; β u represents the enterprise deviation of enterprise user u, that is, the deviation generated by the enterprise itself under this enterprise; ω u represents the personal deviation of enterprise user u, that is, the deviation caused by the individual factors of the enterprise in the enterprise; λ i The text keyword decision vector representing the transaction data parameter i, and the deviation generated in the text keyword;

[0029] S6. Calculate P for all financial transaction data parameters i. u，i , and sum them up, the result is the total preference score of the positive feedback transaction data, recorded as S;

[0030]

[0031] Where K is the number of transaction data expressing positive feedback; m is the number of corresponding financial transaction data parameters;

[0032] Analyze the market style of each positive feedback trading product based on the label, filter out financial transactions with the same market style, and calculate the preference score of enterprise user u for each market style, that is, calculate the sum of all S under the same market style;

[0033] S7. Select the market style whose preference score exceeds the threshold as the market style preferred by enterprise user u, select financial transaction data consistent with the market style preferred by enterprise user u from dataset B, and select financial transaction data consistent with the market style preferred by enterprise user u from dataset C to form dataset D;

[0034] S8. Train the dataset D to obtain the preference score range of various parameters in the enterprise financial transaction data of the enterprise user u in a safe state, and use it as the safe financial transaction range.

[0035] The safe financial transaction range refers to the financial transaction range that meets all transaction parameters. Within this range, if all transaction parameters are met, it proves that the transaction environment and personnel are highly secure.

[0036] According to the above technical solution, the monitoring module includes a comparison unit and an alarm unit;

[0037] The comparison unit is used to store the safe financial transaction range and obtain real-time financial transaction data for comparison; the alarm unit is used to issue an alarm message for financial transactions that do not meet the safe financial transaction range and suspend the financial transaction;

[0038] The output end of the comparison unit is connected to the input end of the alarm unit.

[0039] According to the above technical solution, the prediction module includes a prediction unit and an output unit;

[0040] The prediction unit is used to predict the success rate of the next financial transaction based on big data; the output unit is used to output the result to the administrator for notification;

[0041] The output end of the prediction unit is connected to the input end of the output unit;

[0042] The prediction unit performs prediction including the following steps:

[0043] S9-1. Obtain n sets of financial transaction data of the same enterprise and obtain the secure financial transaction scope of the enterprise;

[0044] S9-2. Select the central value of the safe financial transaction range, i.e., the midpoint value, and calculate the absolute value of the difference between the preference score of each parameter in each set of financial transaction data and its corresponding midpoint value, and record it as the set E = {j1, j2, ..., j m}, m is the number of corresponding financial transaction data parameters; then there are n sets E, denoted as {E1, E2, ..., E n};

[0045] S9-3. For each set E, find the average value and record it as j avc ;

[0046] S9-4, for n sets of sets E avc Here we find the average value, which is recorded as v avc , set the maximum and minimum thresholds v max 、v min , if v avc Beyond v max or v avc Lower than v min , the prediction result is 0; if v avc In v max With v min If the value is between , the prediction result is 1;

[0047] S9-5. A prediction result of 0 represents that the success rate of the next financial transaction is less than 50%; a prediction result of 1 represents that the success rate of the next financial transaction is greater than 50%.

[0048] According to the above technical solution, the blockchain storage module includes a blockchain transaction storage unit and a blockchain alarm storage unit;

[0049] The blockchain transaction storage unit is used to store the financial transaction data of each corporate user; the blockchain alarm storage unit is used to store the generated alarm messages.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] The present invention can provide a monitoring system for monitoring all aspects of financial transactions. Before the monitoring process, a learner suitable for the enterprise itself is first obtained. According to the enterprise's historical data, the operation data of the enterprise users, the enterprise's geographical scope, business premises, transaction nature, transaction objects, specific transaction tools, etc., a comprehensive study of the enterprise is conducted to form an enterprise's own financial transaction system monitoring system, establish a safe financial transaction range, and all transactions within this transaction range are safe and legal transactions. If they do not fall within this transaction range, an alarm message will be issued and the financial transaction will be suspended. It can effectively prevent the occurrence of false transactions, coerced transactions and other bad behaviors in the financial transaction process, and all data will be uploaded to the blockchain storage module to further increase the traceability effect and effectively prevent data loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0053] Figure 1 This is a flowchart of a financial system monitoring system based on blockchain and cloud computing in the present invention;

[0054] Figure 2 This is a schematic diagram of the data processing steps of a financial system monitoring system based on blockchain and cloud computing in the present invention. DETAILED DESCRIPTION

[0055] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0056] See also Figure 1-2, the present invention provides a technical solution:

[0057] A financial system monitoring system based on blockchain and cloud computing, the system includes a data acquisition module, a data analysis module, a data processing module, a monitoring module, a prediction module, and a blockchain storage module;

[0058] The data acquisition module is used to obtain various financial transaction behavior data, including current financial transaction data, financial system transaction data in a secure state, and historical financial system transaction data of users. The data analysis module is used to perform cluster analysis on different financial transaction data and classify them according to different market styles and transaction objects. The data processing module is used to process financial transaction data to derive the user's potential preferred transaction methods. The monitoring module is used to retrieve current financial transactions and compare them with the user's potential preferred transaction methods, issue alarm messages for financial transactions that do not meet a certain similarity, and temporarily block transactions. The prediction module is used to predict the probability of success of the user's next transaction based on the user's transaction behavior data. The blockchain storage module is used to store financial transaction data and alarm data.

[0059] The output end of the data acquisition module is connected to the input end of the data analysis module, the monitoring module, and the blockchain storage module; the output end of the data analysis module is connected to the input end of the data processing module; the output end of the data processing module is connected to the input end of the monitoring module and the prediction module; the output end of the monitoring module is connected to the input end of the blockchain storage module.

[0060] The data acquisition module includes a real-time data acquisition unit and a historical data acquisition unit;

[0061] The real-time data acquisition unit is used to acquire data on real-time financial transactions conducted by enterprise users; the historical data acquisition unit is used to acquire financial transaction data in a secure state and historical financial transaction data of enterprise users.

[0062] The financial transaction data in a safe state refers to normal financial transaction data that is permitted by the state and has passed inspection.

[0063] The data analysis module includes a transaction object analysis unit and a market style analysis unit;

[0064] The transaction object analysis unit is used to analyze financial transaction data according to different transaction objects; the market style analysis unit is used to analyze financial transaction data according to different transaction markets.

[0065] The transaction object analysis unit is divided into public transactions and private transactions according to different transaction objects;

[0066] The market style analysis unit is divided into currency trading, capital trading, foreign exchange trading, gold trading, and securities trading according to different trading markets.

[0067] The data processing module includes a data receiving unit and a data processing unit;

[0068] The data receiving unit is used to receive the transmission data of the data acquisition module and the data analysis module; the data processing unit is used to process the data in the data receiving unit;

[0069] The output end of the data receiving unit is connected to the input end of the data processing unit.

[0070] The processing process of the data processing unit is as follows:

[0071] S1. Obtain real-time financial system transaction content, recorded as Dataset A; obtain financial system transaction data in a secure state, recorded as Dataset B; obtain historical financial system transaction data of enterprise users, recorded as Dataset C;

[0072] S2. Perform cluster analysis on the transaction data in dataset A, clustering them into public transactions and private transactions based on the different types of transaction objects, and extract features from the transaction data using a neural network.

[0073] S3. Classify the trading products in the financial system transaction data in Dataset B according to different market styles and label them with style labels. In Dataset B, each financial transaction includes the geographical scope, business location, transaction nature, transaction object, financing method, and specific transaction tools. Each parameter has a corresponding text description.

[0074] S4. Analyze and process dataset C, learning the user's potential transaction preferences based on the enterprise user's historical financial system transaction data, and obtain positive feedback from the user's implicit feedback. Positive feedback includes transaction time less than X seconds and the number of failures in a single transaction less than Y times. The transaction data set in dataset C is denoted as M, where I represents any transaction data, and M+ represents the set of all financial system transaction data for which the enterprise user expresses positive feedback, and I∈M+. Any parameter in each financial system transaction data set in M+ is denoted as i, and i∈I.

[0075] S5. Based on the transaction data I∈M+ in which the enterprise user has expressed positive feedback, define an enterprise user preference predictor to predict the user's preference for the financial transaction data parameter i, according to the formula:

[0076] P u，i =α+β u +ω u *λ i

[0077] Among them, P u，i represents the preference score of enterprise user u for transaction data parameter i; α represents the global offset; β u represents the enterprise deviation of enterprise user u; ω u represents the personal deviation of enterprise user u; i The text keyword decision vector representing the transaction data parameter i;

[0078] S6. Calculate P for all financial transaction data parameters i. u，i , and sum them up, the result is the total preference score of the positive feedback transaction data, recorded as S;

[0079]

[0080] Where K is the number of transaction data expressing positive feedback; m is the number of corresponding financial transaction data parameters;

[0081] Analyze the market style of each positive feedback trading product based on the label, filter out financial transactions with the same market style, and calculate the preference score of enterprise user u for each market style, that is, calculate the sum of all S under the same market style;

[0082] S7. Select the market style whose preference score exceeds the threshold as the market style preferred by enterprise user u, select financial transaction data consistent with the market style preferred by enterprise user u from dataset B, and select financial transaction data consistent with the market style preferred by enterprise user u from dataset C to form dataset D;

[0083] S8. Train the dataset D to obtain the preference score range of various parameters in the enterprise financial transaction data of the enterprise user u in a safe state, and use it as the safe financial transaction range.

[0084] The monitoring module includes a comparison unit and an alarm unit;

[0085] The comparison unit is used to store the safe financial transaction range and obtain real-time financial transaction data for comparison; the alarm unit is used to issue an alarm message for financial transactions that do not meet the safe financial transaction range and suspend the financial transaction;

[0086] The output end of the comparison unit is connected to the input end of the alarm unit.

[0087] The prediction module includes a prediction unit and an output unit;

[0088] The prediction unit is used to predict the success rate of the next financial transaction based on big data; the output unit is used to output the result to the administrator for notification;

[0089] The output end of the prediction unit is connected to the input end of the output unit;

[0090] The prediction unit performs prediction including the following steps:

[0091] S9-1. Obtain n sets of financial transaction data of the same enterprise and obtain the secure financial transaction scope of the enterprise;

[0092] S9-2. Select the central value of the safe financial transaction range, i.e., the midpoint value, and calculate the absolute value of the difference between the preference score of each parameter in each set of financial transaction data and its corresponding midpoint value, and record it as the set E = {j1, j2, ..., j m}, m is the number of corresponding financial transaction data parameters; then there are n sets E, denoted as {E1, E2, ..., E n};

[0093] S9-3. For each set E, find the average value and record it as j avc ;

[0094] S9-4, for n sets of sets E avc Here we find the average value, which is recorded as v avc , set the maximum and minimum thresholds v max 、v min , if v avc Beyond v max or v avc Lower than v min , the prediction result is 0; if v avc In v max With v min If the value is between , the prediction result is 1;

[0095] S9-5. A prediction result of 0 represents that the success rate of the next financial transaction is less than 50%; a prediction result of 1 represents that the success rate of the next financial transaction is greater than 50%.

[0096] The blockchain storage module includes a blockchain transaction storage unit and a blockchain alarm storage unit;

[0097] The blockchain transaction storage unit is used to store the financial transaction data of each corporate user; the blockchain alarm storage unit is used to store the generated alarm messages.

[0098] In this embodiment:

[0099] Obtain real-time financial system transaction content, recorded as Dataset A; obtain financial system transaction data in a secure state, recorded as Dataset B; obtain historical financial system transaction data of enterprise users, recorded as Dataset C;

[0100] Perform cluster analysis on the transaction data in dataset A and categorize them into public transactions and private transactions based on the different types of transaction objects.

[0101] The trading products in the financial system transaction data in dataset B are classified according to different market styles and labeled with style labels; there are 100 currency transactions, 100 capital transactions, 50 foreign exchange transactions, 50 gold transactions, and 50 securities transactions;

[0102] In Dataset B, each financial transaction includes the geographical scope, business location, transaction nature, transaction object, financing method, and specific transaction tools. Each parameter has a corresponding text description;

[0103] Analyze and process data set C;

[0104] Positive feedback includes transaction time less than 60 seconds and fewer than 1 failed transaction in a single transaction;

[0105] The transaction data set in dataset C is denoted as M, where I represents any transaction data, M+ represents the set of all financial system transaction data in which enterprise users express positive feedback, and I∈M+; any parameter in each financial system transaction data set in M+ is denoted as i, and i∈I;

[0106] There are 10 groups in M+; the parameter i has three items, namely geographical scope, business location, and specific trading tools;

[0107] There is an enterprise user u;

[0108] Based on the transaction data I∈M+ in which enterprise users have expressed positive feedback, we define an enterprise user preference predictor to predict the user's preference for the financial transaction data parameter i, according to the formula:

[0109] P u，i =α+β u +ω u *λ i

[0110] Among them, P u，i represents the preference score of enterprise user u for transaction data parameter i; α represents the global offset; β u represents the enterprise deviation of enterprise user u; ω u represents the personal deviation of enterprise user u; i The text keyword decision vector representing the transaction data parameter i;

[0111] S6. Calculate P for all financial transaction data parameters i. u，i , and sum them up, the result is the total preference score of the positive feedback transaction data, recorded as S;

[0112]

[0113] Where K is the number of transaction data expressing positive feedback; m is the number of corresponding financial transaction data parameters;

[0114] Analyze the market style of each positive feedback trading product based on the label, filter out financial transactions with the same market style, and calculate the preference score of enterprise user u for each market style, that is, calculate the sum of all S under the same market style;

[0115] A total of 10 groups of S were obtained by calculation;

[0116] Set the threshold to S max ; It is found that there are S1 to S9 that satisfy S max ;Preferred market style is currency trading;

[0117] Select financial transaction data that is consistent with the market style preferred by enterprise user u from dataset B, and select financial transaction data that is consistent with the market style preferred by enterprise user u from dataset C to form dataset D;

[0118] Train the dataset D to obtain the preference score range of various parameters in the financial transaction data of the enterprise user u in a secure state, and use it as the secure financial transaction range;

[0119] The scope of safe financial transactions is within a 50-meter radius of place O; the business premises are within a 50-meter radius of place O2, and the specific transaction tools are O3 cards or O4 cards.

[0120] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0121] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A financial system monitoring system based on blockchain and cloud computing, characterized by: The system includes a data acquisition module, a data analysis module, a data processing module, a monitoring module, a prediction module, and a blockchain storage module; The data acquisition module is used to obtain various financial transaction behavior data, including current financial transaction data, financial system transaction data in a secure state, and historical financial system transaction data of users. The data analysis module is used to perform cluster analysis on different financial transaction data and classify them according to different market styles and transaction objects. The data processing module is used to process financial transaction data to derive the user's potential preferred transaction methods. The monitoring module is used to retrieve current financial transactions and compare them with the user's potential preferred transaction methods, issue alarm messages for financial transactions that do not meet a certain similarity, and temporarily block transactions. The prediction module is used to predict the probability of success of the user's next transaction based on the user's transaction behavior data. The blockchain storage module is used to store financial transaction data and alarm data. The output end of the data acquisition module is connected to the input end of the data analysis module, the monitoring module, and the blockchain storage module; the output end of the data analysis module is connected to the input end of the data processing module; the output end of the data processing module is connected to the input end of the monitoring module and the prediction module; the output end of the monitoring module is connected to the input end of the blockchain storage module; The data processing module includes a data receiving unit and a data processing unit; The data receiving unit is used to receive the transmission data of the data acquisition module and the data analysis module; the data processing unit is used to process the data in the data receiving unit; The output end of the data receiving unit is connected to the input end of the data processing unit; The processing process of the data processing unit is as follows: S1. Obtain real-time financial system transaction content, recorded as a data set ; Obtain financial system transaction data in a secure state, recorded as a data set ; Obtain historical financial system transaction data of enterprise users, recorded as data set ; S2. Dataset Cluster analysis is performed on transaction data, and clustering is performed based on the different types of transaction objects to form public transactions and private transactions; S3, the dataset The trading products in the financial system trading data in the dataset are classified according to different market styles and annotated with style labels; In the data, each financial transaction includes geographical scope, business location, transaction nature, transaction object, financing method, and specific transaction tools. Each parameter has a corresponding text description. S4. Dataset Analyze and process the user's historical financial system transaction data to learn the user's potential transaction preferences and obtain positive feedback from the user's implicit feedback, including transaction time below Seconds and the number of failures in a single transaction is less than times; the dataset The transaction data set in , Represents any transaction data, represents the set of all financial system transaction data for which enterprise users express positive feedback, and ; Any parameter in each financial system transaction data set is recorded as ,and ; S5. Transaction data based on positive feedback from enterprise users , define an enterprise user preference predictor to predict the user's preference for financial transaction data parameters Preference, according to the formula: ； in, Indicates enterprise users For transaction data parameters preference score; Indicates the global offset; Indicates enterprise users The amount of enterprise deviation; Indicates enterprise users the amount of personal bias; Indicates transaction data parameters The text keywords determine the vector; S6. All financial transaction data parameters Find them separately , and sum them up, the result is the total preference score of the positive feedback transaction data, recorded as ; ； in, is the number of transaction data expressing positive feedback; is the number of corresponding financial transaction data parameters; Analyze the market style of each positive feedback trading product based on the label, filter out financial transactions with the same market style, and calculate the number of corporate users. The preference score for each market style, that is, calculating the preference score for all the the sum of; S7. Select market styles whose preference scores exceed the threshold as enterprise users The preferred market style and from the data set Choose from enterprise users Preferred market style consistent financial trading data, from the dataset Choose from enterprise users Financial transaction data consistent with the preferred market style constitutes the data set ; S8. Dataset Conduct training to obtain enterprise users in a safe state The preference score range of various parameters in the company's financial transaction data is used as the safe financial transaction range.

2. The financial system monitoring system based on blockchain and cloud computing according to claim 1, characterized in that: The data acquisition module includes a real-time data acquisition unit and a historical data acquisition unit; The real-time data acquisition unit is used to acquire data on real-time financial transactions conducted by enterprise users; the historical data acquisition unit is used to acquire financial transaction data in a secure state and historical financial transaction data of enterprise users.

3. The financial system monitoring system based on blockchain and cloud computing according to claim 2, characterized in that: The financial transaction data in a safe state refers to normal financial transaction data that is permitted by the state and has passed inspection.

4. The financial system monitoring system based on blockchain and cloud computing according to claim 3, characterized in that: The data analysis module includes a transaction object analysis unit and a market style analysis unit; The transaction object analysis unit is used to analyze financial transaction data according to different transaction objects; the market style analysis unit is used to analyze financial transaction data according to different transaction markets.

5. The financial system monitoring system based on blockchain and cloud computing according to claim 4, characterized in that: The transaction object analysis unit is divided into public transactions and private transactions according to different transaction objects; The market style analysis unit is divided into currency trading, capital trading, foreign exchange trading, gold trading, and securities trading according to different trading markets.

6. The financial system monitoring system based on blockchain and cloud computing according to claim 5, characterized in that: The monitoring module includes a comparison unit and an alarm unit; The comparison unit is used to store the safe financial transaction range and obtain real-time financial transaction data for comparison; the alarm unit is used to issue an alarm message for financial transactions that do not meet the safe financial transaction range and suspend the financial transaction; The output end of the comparison unit is connected to the input end of the alarm unit.

7. The financial system monitoring system based on blockchain and cloud computing according to claim 6, characterized in that: The prediction module includes a prediction unit and an output unit; The prediction unit is used to predict the success rate of the next financial transaction based on big data; the output unit is used to output the result to the administrator for notification; The output end of the prediction unit is connected to the input end of the output unit; The prediction unit performs prediction including the following steps: S9-1. Get the same company Group financial transaction data to obtain the enterprise's secure financial transaction scope; S9-2. Select the central value of the safe financial transaction range, that is, the midpoint value, and calculate the absolute value of the difference between the preference score of each parameter in each set of financial transaction data and its corresponding midpoint value, and record it as the set , is the number of corresponding financial transaction data parameters; if Group Collection , respectively ; S9-3. For each set , find the average value and record it as ; S9-4, yes Group Collection of Here we find the average value, which is recorded as , set the maximum and minimum thresholds 、 ,like Beyond or Lower than , the prediction result is 0; if exist and If the value is between , the prediction result is 1; S9-5. A prediction result of 0 indicates that the success rate of the next financial transaction is less than 50%; a prediction result of 1 indicates that the success rate of the next financial transaction is greater than 50%.

8. The financial system monitoring system based on blockchain and cloud computing according to claim 1, characterized in that: The blockchain storage module includes a blockchain transaction storage unit and a blockchain alarm storage unit; The blockchain transaction storage unit is used to store the financial transaction data of each corporate user; the blockchain alarm storage unit is used to store the generated alarm messages.

Images