Financial data real-time risk monitoring intelligent early warning method and system

Abstract

The invention provides a financial data real-time risk monitoring intelligent early warning method and system, and the method comprises the steps: carrying out the classification and recognition of financial data, and obtaining a classification result; according to a classification result, calling a corresponding risk monitoring early warning library; analyzing the financial data based on the called risk monitoring and early warning library to obtain a first risk analysis result; and when the first risk analysis result meets a pre-configured first early warning condition, outputting corresponding early warning information. According to the financial data real-time risk monitoring intelligent early warning method and system, real-time risk monitoring is realized, the corresponding risk monitoring early warning library is adaptively selected according to the classification condition of the financial data during monitoring, and accurate risk early warning is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of early warning management systems, and in particular to an intelligent early warning method and system for real-time risk monitoring of financial data. Background Art

[0002] Financial data refers to various data related to the financial industry, including: business data, market data, transaction data, risk data, etc. of financial institutions. The management and analysis of financial data is of great significance to financial institutions and investors, and can help better manage risks, formulate investment strategies, improve operational efficiency, etc. Financial data is directly related to the interests of users; how to achieve real-time risk monitoring is of great significance. Summary of the invention

[0003] One of the purposes of the present invention is to provide a method and system for real-time risk monitoring and intelligent early warning of financial data, so as to realize real-time risk monitoring. During monitoring, the corresponding risk monitoring and early warning library is adaptively selected according to the classification of financial data to realize accurate risk early warning.

[0004] An embodiment of the present invention provides a financial data real-time risk monitoring intelligent early warning method, comprising: Classify and identify financial data to obtain classification results; According to the classification results, the corresponding risk monitoring and early warning database is retrieved; Based on the retrieved risk monitoring and early warning database, the financial data is analyzed to obtain the first risk analysis result; When the first risk analysis result meets the pre-configured first warning condition, the corresponding warning information is output.

[0005] Preferably, the classification and identification of financial data is based on a preconfigured classification and identification tree.

[0006] Preferably, the corresponding risk monitoring and early warning library is retrieved based on the classification result; wherein the risk monitoring and early warning library is pre-configured and corresponds to the tree structure code assigned to each terminal node of the classification identification tree.

[0007] Preferably, analyzing the financial data based on the retrieved risk monitoring and early warning database to obtain a first risk analysis result includes: The feature extraction table corresponding to the risk monitoring and early warning database is used to extract features from financial data, and a feature set corresponding to the financial data is constructed based on the extracted feature parameters; Based on the feature set, the risk monitoring and early warning database is fully indexed and the corresponding first risk analysis result is retrieved.

[0008] Preferably, the financial data real-time risk monitoring intelligent early warning method further includes: Conduct risk analysis on the source and transmission path of financial data to determine the second risk analysis result; When the second risk analysis result meets the pre-configured second warning condition, output corresponding warning information; The steps for risk analysis of the source and transmission path of financial data are as follows: According to the source risk correspondence table, the risk of the source of the financial data is quantified to obtain a first risk parameter; According to the node risk correspondence table, the risk of each node on the transmission path is quantified to obtain a second risk parameter; A transmission risk value of the financial data is calculated based on the first risk parameter and the second risk parameter.

[0009] The present invention also provides a real-time risk monitoring intelligent early warning system for financial data, comprising: a classification module, a retrieval module, an analysis module and an early warning module; wherein the classification module classifies and identifies financial data to obtain classification results; the retrieval module retrieves the corresponding risk monitoring and early warning library based on the classification results; the analysis module analyzes the financial data based on the retrieved risk monitoring and early warning library to obtain a first risk analysis result; when the first risk analysis result meets the pre-configured first early warning condition, the early warning module outputs the corresponding early warning information.

[0010] Preferably, the classification and identification of financial data is based on a preconfigured classification and identification tree.

[0011] Preferably, the risk monitoring and early warning library is pre-configured and associated with the tree structure code assigned to each terminal node of the classification and identification tree.

[0012] Preferably, the analysis module includes: a construction unit and an index unit; wherein the construction unit uses a feature extraction table corresponding to the risk monitoring and early warning library to extract features from the financial data, and constructs a feature set corresponding to the financial data based on the extracted feature parameters; the index unit indexes the entire risk monitoring and early warning library based on the feature set, and retrieves the corresponding first risk analysis result.

[0013] Preferably, the financial data real-time risk monitoring intelligent early warning system further includes: a transmission path analysis module; wherein the transmission path analysis module performs risk analysis on the source and transmission path of the financial data to determine a second risk analysis result; when the second risk analysis result meets the pre-configured second early warning condition, the early warning module outputs corresponding early warning information; Among them, the transmission path analysis module includes a source analysis unit, a node analysis unit and a comprehensive analysis unit: the source analysis unit quantifies the risk of the source of the financial data according to the source risk correspondence table to obtain a first risk parameter; the node analysis unit quantifies the risk of each node on the transmission path according to the node risk correspondence table to obtain a second risk parameter; the comprehensive analysis unit calculates the transmission risk value of the financial data based on the first risk parameter and the second risk parameter.

[0014] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0015] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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: Figure 1 A schematic diagram of an intelligent early warning method for real-time risk monitoring of financial data in an embodiment of the present invention; Figure 2 Schematic diagram of an intelligent early warning system for real-time risk monitoring of financial data in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0018] The embodiment of the present invention provides a method for real-time risk monitoring and intelligent early warning of financial data. Figure 1 As shown, including: Step 1: Classify and identify financial data to obtain classification results; The classification and identification of financial data is based on a pre-configured classification and identification tree; the classification and identification tree is constructed in advance, for example: "individual", "institution" and "public" are the first-level branch nodes; "identity information", "asset information" and "transaction records" are the second-level branch nodes under the branch corresponding to "individual"; "customer transaction records", "risk management" and "balance sheet" are the second-level branch nodes under the branch corresponding to "institution"; "market", "macroeconomics" and "industry" are the second-level branch nodes under the branch corresponding to "public"; "income" and "expenditure" are the terminal nodes under the second-level branch nodes corresponding to "transaction records"; the financial data is classified and identified to locate the specific situation of the financial data; the specific operation of classification and identification is to extract features from the financial data and construct a feature data set of the financial data based on the extracted feature parameters; match the feature data set with each standard data set in the identification database corresponding to each terminal node; the classification result represented by the terminal node with the largest matching degree is used as the classification result of the financial data; wherein, the matching can be achieved by calculating the similarity between the feature data set and the standard data set; Step 2: Based on the classification results, retrieve the corresponding risk monitoring and early warning database; The platform server stores multiple risk monitoring and early warning libraries, that is, the risk monitoring and early warning libraries are pre-configured and associated with the tree structure codes assigned to each terminal node of the classification identification tree; the tree structure codes are assigned according to the tree structure, including: fields of all upper node numbers of the terminal node and fields of the terminal node number; different risk monitoring and early warning libraries are configured to cope with different risk monitoring requirements required by different types of data; Step 3: Analyze the financial data based on the retrieved risk monitoring and early warning database to obtain a first risk analysis result; The specific analysis process includes: using the feature extraction table corresponding to the risk monitoring and early warning library to extract features from the financial data, and constructing a feature set corresponding to the financial data based on the extracted feature parameters; based on the feature set, indexing the risk monitoring and early warning library in its entirety, and retrieving the corresponding first risk analysis result; taking the classification result corresponding to the "expenditure" terminal node as an example, the features to be extracted include: amount, expenditure time, identity identification code of the payment object, etc., and then arranging the extracted features in order to form feature parameters, and the corresponding first risk analysis results include: no risk (expenditure is average and the amount is less than or equal to the preset threshold), low risk (expenditure is relatively concentrated and the amount is less than or equal to the preset amount threshold), high risk (expenditure is concentrated and the amount is greater than the preset amount threshold); Step 4: When the first risk analysis result meets the pre-configured first warning condition, output corresponding warning information; When the configured first warning condition is a high-risk warning and the first risk analysis result is a high risk, "expenditure high-risk customers" is output.

[0019] There is a risk of malicious tampering during the generation and transmission of financial data. In one embodiment, the method for intelligent early warning of real-time risk monitoring of financial data also includes: Conduct risk analysis on the source and transmission path of financial data to determine the second risk analysis result; When the second risk analysis result meets the pre-configured second warning condition, output corresponding warning information; The steps for risk analysis of the source and transmission path of financial data are as follows: According to the source risk correspondence table, the risk of the source of the financial data is quantified to obtain the first risk parameter; the source risk correspondence table is pre-configured, and the source in the table corresponds to the first risk parameter one by one; the source includes: third-party platform data, fixed terminal input, mobile terminal input, etc.; According to the node risk correspondence table, the risk of each node on the transmission path is quantified to obtain the second risk parameter; the node risk correspondence table is also configured in advance, and the node risk correspondence table is queried according to the node type, whether the node is registered, and other node situation description data to obtain the corresponding second risk parameter; Calculate the transmission risk value of the financial data based on the first risk parameter and the second risk parameter. The transmission risk value is the weighted sum of each data of the first risk parameter and the second risk parameter and the corresponding pre-configured weight; The working principle and beneficial effects of the above technical solution are: Comprehensive analysis is conducted on the source and transmission path of financial data to determine the transmission risk value of financial data; the higher the transmission risk value, the higher the possibility of tampering; conversely, the lower the transmission risk value, the more credible the financial data is, which can be used as a basis for whether to use the data as analysis data to ensure the accuracy and effectiveness of the final analysis results. Among them, the second warning condition includes: the transmission risk value is greater than or equal to the preset risk threshold.

[0020] In one embodiment, the financial data real-time risk monitoring intelligent early warning method further includes: Analyze financial data, determine the target objects corresponding to the financial data, and classify and store the financial data according to different target objects; Extract the financial data stored in the same target object, and construct a financial data analysis axis based on the extracted financial data; Based on the financial data analysis axis, build a risk monitoring data set for the target object; Based on the risk monitoring data set, the financial data of the target object obtained in real time is monitored, and an early warning is issued to the target object when an abnormality is detected; In this embodiment, the intelligent early warning method for real-time risk monitoring of financial data analyzes the historical financial data of the target object to obtain a risk monitoring data set, and on this basis monitors the financial data of the target object acquired in real time later, so as to realize real-time monitoring based on the rules summarized by historical financial data analysis, so as to issue early warnings and improve the financial security of the target object; a specific example is: through the analysis of the stored financial data, it is concluded that the financial data of the target object are all generated between 8:00 and 18:00, and when the financial data is generated outside this time range, an early warning needs to be issued; in addition, the risk monitoring data set is also configured with early warning restrictions in dimensions such as the amount threshold of the transaction corresponding to the financial data and the distance threshold between two adjacent transactions; Among them, based on the financial data analysis axis, a risk monitoring data set for the target object is constructed, including: Count the time distribution of each financial data on the financial data analysis axis, and build a warning threshold time range based on the time distribution; for example, count the time when the earliest and latest financial data are generated on a daily basis, and use the largest statistical time range as the warning threshold time range; and / or, The data volume within the preset sampling time (for example, 1 minute to 10 minutes) on the statistical financial data analysis axis is configured based on the maximum data volume. The frequency threshold limits the number of financial data that can be generated by the target object within a certain period of time. The number of times exceeding the frequency threshold can be regarded as abnormal and an early warning is issued. and / or, A safety area is demarcated on a pre-configured map according to the location where each financial data is generated on the financial data analysis axis; the safety area is a closed area formed by sequentially connecting the locations of the outermost circle; for example, the map is a regional map of each administrative district (prefectural-level city, county, township, etc.) stored in the system; the corresponding map is retrieved according to the administrative district to which the location where the financial data is generated belongs; When the location of real-time financial data is not in the safe area, it is considered abnormal; and / or, Calculate the distance between the positions of two adjacent financial data on the financial data analysis axis, and use the maximum value of the distance value as the distance threshold; when the distance between the real-time financial data and the position of the previous financial data exceeds the distance threshold, it is judged as abnormal; The output of the warning can be sent through the mobile terminal corresponding to the target object, and the user can provide feedback based on the actual situation; when the feedback is negative (not permitted), the target object is prohibited from generating financial data; when the feedback is positive (permitted), the target object is allowed to continue to generate financial data; Of course, when the feedback is positive, a time threshold needs to be configured, that is, no tracking and warning of real-time financial data is performed within the time threshold; The time threshold can be determined by the following steps: According to the scoring table corresponding to each monitoring item in the risk detection data set, the value of the current value corresponding to each monitoring item that triggers the warning and exceeds the warning value (when the warning value is a range value, the value is calculated with a boundary value close to the current value) is scored and quantified to obtain a quantitative scoring value; the larger the difference in the scoring table, the larger the quantitative scoring value; Determine the time threshold from a pre-configured branch and time threshold comparison table according to the sum of the quantitative score values; Analyze the target object's situation to set a reasonable and appropriate time threshold to ensure that the number of reminders is reduced as much as possible; the time threshold in the time threshold comparison table corresponds to the quantitative score value one by one, and the larger the quantitative score value, the larger the time threshold; When the time threshold has passed, when the real-time financial data is analyzed for the first time and it is still judged as abnormal and the feedback received after the warning is still positive, a correction value retrieved from the pre-configured correction library based on the number of warnings is added to the time threshold as a new time threshold; When the above event (when analyzing the real-time financial data for the first time after the time threshold, it is still judged as abnormal and the feedback received after the warning is still positive) occurs for the preset first number of times (any one from 3 to 10 times), the new financial data is added to the analysis data, the target object is analyzed again, and a new risk monitoring data set is obtained; In addition, each time the financial data is monitored and analyzed, the deficiency score corresponding to each monitoring item is determined based on the warning deficiency value of the current value corresponding to each monitoring item in the risk detection data set (that is, the difference between the warning value and the current value that does not trigger a warning) and the pre-configured deficiency score; when the number of consecutive preset deficiencies (anywhere from 10 to 100 times) exceeds the preset score threshold, the newly generated financial data is re-analyzed to obtain a new risk monitoring data set.

[0021] In addition, it is also possible to analyze the objects in the financial data where financial events have occurred, determine the risk value of the object, and issue an early warning when the risk value is greater than the preset threshold; Among them, the risk value is obtained by analyzing the authority and historical financial data of the object in the system; the specific analysis steps are as follows: extract the evaluation data in the historical financial data, calculate the evaluation value corresponding to each evaluation data according to the pre-configured evaluation quantitative template, query the pre-configured first risk table according to the average of the evaluation value, and determine the first value; query the pre-configured second risk table according to the authority, and determine the second value; extract the features of the financial data, and then extract the third value from the pre-configured third value library according to the extracted feature parameters; the sum of the first value, the second value and the third value is used as the risk value; The characteristic parameters include: the mean, maximum and minimum of the transaction amount; the mean, maximum and minimum of the transaction frequency in each time period; and the third value in the third value table is associated with the characteristic parameter in a one-to-one correspondence.

[0022] The present invention also provides a financial data real-time risk monitoring intelligent early warning system, such as Figure 2 As shown, it includes: a classification module 1, a retrieval module 2, an analysis module 3 and an early warning module 4; wherein, the classification module 1 classifies and identifies the financial data to obtain a classification result; the retrieval module 2 retrieves the corresponding risk monitoring and early warning library based on the classification result; the analysis module 3 analyzes the financial data based on the retrieved risk monitoring and early warning library to obtain a first risk analysis result; when the first risk analysis result meets the pre-configured first early warning condition, the early warning module 4 outputs the corresponding early warning information.

[0023] Among them, the classification and identification of financial data is based on a pre-configured classification and identification tree.

[0024] Among them, the risk monitoring and early warning library is pre-configured and corresponds to the tree structure code assigned to each terminal node of the classification and recognition tree.

[0025] Among them, the analysis module includes: a construction unit and an index unit; wherein the construction unit uses the feature extraction table corresponding to the risk monitoring and early warning library to extract features from the financial data, and constructs a feature set corresponding to the financial data based on the extracted feature parameters; the index unit indexes the entire risk monitoring and early warning library based on the feature set, and retrieves the corresponding first risk analysis result.

[0026] In one embodiment, the financial data real-time risk monitoring intelligent early warning system further includes: a transmission path analysis module; wherein the transmission path analysis module performs risk analysis on the source and transmission path of the financial data to determine a second risk analysis result; when the second risk analysis result meets the pre-configured second early warning condition, the early warning module outputs corresponding early warning information; Among them, the transmission path analysis module includes a source analysis unit, a node analysis unit and a comprehensive analysis unit: the source analysis unit quantifies the risk of the source of the financial data according to the source risk correspondence table to obtain a first risk parameter; the node analysis unit quantifies the risk of each node on the transmission path according to the node risk correspondence table to obtain a second risk parameter; the comprehensive analysis unit calculates the transmission risk value of the financial data based on the first risk parameter and the second risk parameter.

[0027] In one embodiment, the financial data real-time risk monitoring intelligent early warning system further includes: a tracking and analysis module; the tracking and analysis module performs the following operations: Analyze financial data, determine the target objects corresponding to the financial data, and classify and store the financial data according to different target objects; Extract the financial data stored in the same target object, and construct a financial data analysis axis based on the extracted financial data; Based on the financial data analysis axis, build a risk monitoring data set for the target object; Based on the risk monitoring data set, the financial data of the target object obtained in real time is monitored, and an early warning is issued to the target object when an abnormality is detected; In this embodiment, the financial data real-time risk monitoring intelligent early warning system analyzes the historical financial data of the target object to obtain a risk monitoring data set, and on this basis monitors the financial data of the target object acquired in real time later, thereby realizing real-time monitoring based on the rules summarized through historical financial data analysis, so as to issue early warnings and improve the financial security of the target object; a specific example is: through the analysis of the stored financial data, it is concluded that the financial data of the target object are all generated between 8:00 and 18:00, and when the financial data is generated outside this time range, an early warning needs to be issued; in addition, the risk monitoring data set is also configured with early warning restrictions in dimensions such as the amount threshold of the transaction corresponding to the financial data and the distance threshold between two adjacent transactions; Among them, based on the financial data analysis axis, a risk monitoring data set for the target object is constructed, including: Count the time distribution of each financial data on the financial data analysis axis, and build a warning threshold time range based on the time distribution; for example, count the time when the earliest and latest financial data are generated on a daily basis, and use the largest statistical time range as the warning threshold time range; and / or, The data volume within the preset sampling time (for example, 1 minute to 10 minutes) on the statistical financial data analysis axis is configured based on the maximum data volume. The frequency threshold limits the number of financial data that can be generated by the target object within a certain period of time. The number of times exceeding the frequency threshold can be regarded as abnormal and an early warning is issued. and / or, A safety area is demarcated on a pre-configured map according to the location where each financial data is generated on the financial data analysis axis; the safety area is a closed area formed by sequentially connecting the locations of the outermost circle; for example, the map is a regional map of each administrative district (prefectural-level city, county, township, etc.) stored in the system; the corresponding map is retrieved according to the administrative district to which the location where the financial data is generated belongs; When the location of real-time financial data is not in the safe area, it is considered abnormal; and / or, Calculate the distance between the positions of two adjacent financial data on the financial data analysis axis, and use the maximum value of the distance value as the distance threshold; when the distance between the real-time financial data and the position of the previous financial data exceeds the distance threshold, it is judged as abnormal; The output of the warning can be sent through the mobile terminal corresponding to the target object, and the user can provide feedback based on the actual situation; when the feedback is negative (not permitted), the target object is prohibited from generating financial data; when the feedback is positive (permitted), the target object is allowed to continue to generate financial data; Of course, when the feedback is positive, a time threshold needs to be configured, that is, no tracking and warning of real-time financial data is performed within the time threshold; The time threshold can be determined by the following steps: According to the scoring table corresponding to each monitoring item in the risk detection data set, the value of the current value corresponding to each monitoring item that triggers the warning and exceeds the warning value (when the warning value is a range value, the value is calculated with a boundary value close to the current value) is scored and quantified to obtain a quantitative scoring value; the larger the difference in the scoring table, the larger the quantitative scoring value; Determine the time threshold from a pre-configured branch and time threshold comparison table according to the sum of the quantitative score values; Analyze the target object's situation to set a reasonable and appropriate time threshold to ensure that the number of reminders is reduced as much as possible; the time threshold in the time threshold comparison table corresponds to the quantitative score value one by one, and the larger the quantitative score value, the larger the time threshold; When the time threshold has passed, when the real-time financial data is analyzed for the first time and it is still judged as abnormal and the feedback received after the warning is still positive, a correction value retrieved from the pre-configured correction library based on the number of warnings is added to the time threshold as a new time threshold; When the above event (when analyzing the real-time financial data for the first time after the time threshold, it is still judged as abnormal and the feedback received after the warning is still positive) occurs for the preset first number of times (any one from 3 to 10 times), the new financial data is added to the analysis data, the target object is analyzed again, and a new risk monitoring data set is obtained; In addition, each time the financial data is monitored and analyzed, the deficiency score corresponding to each monitoring item is determined based on the warning deficiency value of the current value corresponding to each monitoring item in the risk detection data set (that is, the difference between the warning value and the current value that does not trigger a warning) and the pre-configured deficiency score; when the number of consecutive preset deficiencies (anywhere from 10 to 100 times) exceeds the preset score threshold, the newly generated financial data is re-analyzed to obtain a new risk monitoring data set.

[0028] In addition, it is also possible to analyze the objects in the financial data where financial events have occurred, determine the risk value of the object, and issue an early warning when the risk value is greater than the preset threshold; Among them, the risk value is obtained by analyzing the authority and historical financial data of the object in the system; the specific analysis steps are as follows: extract the evaluation data in the historical financial data, calculate the evaluation value corresponding to each evaluation data according to the pre-configured evaluation quantitative template, query the pre-configured first risk table according to the average of the evaluation value, and determine the first value; query the pre-configured second risk table according to the authority, and determine the second value; extract the features of the financial data, and then extract the third value from the pre-configured third value library according to the extracted feature parameters; the sum of the first value, the second value and the third value is used as the risk value; The characteristic parameters include: the mean, maximum and minimum of the transaction amount; the mean, maximum and minimum of the transaction frequency in each time period; and the third value in the third value table is associated with the characteristic parameter in a one-to-one correspondence.

[0029] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for real-time risk monitoring and intelligent early warning of financial data, characterized in that: include: Classify and identify financial data to obtain classification results; According to the classification results, the corresponding risk monitoring and early warning database is retrieved; Based on the retrieved risk monitoring and early warning database, the financial data is analyzed to obtain the first risk analysis result; When the first risk analysis result meets the pre-configured first warning condition, the corresponding warning information is output.

2. The intelligent early warning method for real-time risk monitoring of financial data according to claim 1, characterized in that: The classification and recognition of financial data is based on a pre-configured classification and recognition tree.

3. The intelligent early warning method for real-time risk monitoring of financial data according to claim 1, characterized in that: According to the classification result, the corresponding risk monitoring and early warning library is retrieved; wherein the risk monitoring and early warning library is pre-configured and corresponds to the tree structure code assigned to each terminal node of the classification identification tree.

4. The intelligent early warning method for real-time risk monitoring of financial data according to claim 1, characterized in that: Based on the retrieved risk monitoring and early warning database, the financial data is analyzed to obtain the first risk analysis results, including: The feature extraction table corresponding to the risk monitoring and early warning database is used to extract features from financial data, and a feature set corresponding to the financial data is constructed based on the extracted feature parameters; Based on the feature set, the risk monitoring and early warning database is fully indexed and the corresponding first risk analysis result is retrieved.

5. The intelligent early warning method for real-time risk monitoring of financial data according to claim 1, characterized in that: Also includes: Conduct risk analysis on the source and transmission path of financial data to determine the second risk analysis result; When the second risk analysis result meets the pre-configured second warning condition, output corresponding warning information; The steps for risk analysis of the source and transmission path of financial data are as follows: According to the source risk correspondence table, the risk of the source of the financial data is quantified to obtain a first risk parameter; According to the node risk correspondence table, the risk of each node on the transmission path is quantified to obtain a second risk parameter; A transmission risk value of the financial data is calculated based on the first risk parameter and the second risk parameter.

6. A financial data real-time risk monitoring intelligent early warning system, characterized in that: include: A classification module, a retrieval module, an analysis module and an early warning module; wherein the classification module classifies and identifies financial data to obtain classification results; the retrieval module retrieves the corresponding risk monitoring and early warning library based on the classification results; the analysis module analyzes the financial data based on the retrieved risk monitoring and early warning library to obtain a first risk analysis result; when the first risk analysis result meets the pre-configured first early warning condition, the early warning module outputs the corresponding early warning information.

7. The financial data real-time risk monitoring intelligent early warning system according to claim 6, characterized in that: The classification and recognition of financial data is based on a pre-configured classification and recognition tree.

8. The financial data real-time risk monitoring intelligent early warning system according to claim 6, characterized in that: The risk monitoring and early warning library is pre-configured and associated with the tree structure code assigned to each terminal node of the classification recognition tree.

9. The financial data real-time risk monitoring intelligent early warning system according to claim 6, characterized in that: The analysis module includes: a construction unit and an index unit; wherein the construction unit uses the feature extraction table corresponding to the risk monitoring and early warning library to extract features from the financial data, and constructs a feature set corresponding to the financial data based on the extracted feature parameters; the index unit indexes the entire risk monitoring and early warning library based on the feature set, and retrieves the corresponding first risk analysis result.

10. The financial data real-time risk monitoring intelligent early warning system according to claim 6, characterized in that: Also includes: A transmission path analysis module; wherein the transmission path analysis module performs risk analysis on the source and transmission path of the financial data to determine a second risk analysis result; when the second risk analysis result meets a pre-configured second warning condition, the warning module outputs corresponding warning information; Among them, the transmission path analysis module includes a source analysis unit, a node analysis unit and a comprehensive analysis unit: the source analysis unit quantifies the risk of the source of the financial data according to the source risk correspondence table to obtain a first risk parameter; the node analysis unit quantifies the risk of each node on the transmission path according to the node risk correspondence table to obtain a second risk parameter; the comprehensive analysis unit calculates the transmission risk value of the financial data based on the first risk parameter and the second risk parameter.

Images