A method and system for dynamic supervision of business information based on big data

Abstract

The present invention discloses a method and system for dynamic supervision of business information based on big data, and relates to the field of dynamic supervision technology. It includes collecting recent business activity data, and using a dynamic clustering algorithm to divide corporate behaviors into cluster groups, identifying companies that deviate from normal behavior groups according to the degree of behavioral deviation; establishing a dynamically updated behavioral baseline model for each cluster group, and dynamically adjusting the baseline according to the latest data; based on the degree of deviation and the behavioral baseline model, conducting real-time risk assessment of the company's business behavior, and triggering graded warnings; according to the graded warning results, triggering a dynamic rule engine to automatically adjust the supervision rules. The present invention uses a dynamic clustering algorithm to group corporate behaviors in real time, identifies abnormal behavior companies according to the degree of behavioral deviation, and establishes a dynamically updated behavioral baseline model based on group behavior characteristics, which can adjust the baseline according to the latest data, thereby improving the adaptability and response speed of the supervision system.

Description

Technical Field

[0001] The present invention relates to the field of dynamic supervision technology, and in particular to a method and system for dynamic supervision of business information based on big data. Background Art

[0002] In recent years, with the rapid development of information technology and big data, business management and operational information analysis based on big data has gradually become one of the core tools for enterprises and government supervision. Big data technology can extract valuable information from massive data and provide a scientific basis for decision-making. In this context, many enterprises and regulatory agencies have begun to rely on data-driven methods, using dynamic monitoring and prediction models to optimize business management, improve corporate benefits, and avoid risks.

[0003] However, existing technologies have certain limitations in dealing with rapidly changing market environments and complex and ever-changing business behaviors. For example, most existing business behavior analysis methods are often based on static modeling based on historical data, which cannot adapt to real-time changes in corporate behavior and market environment; secondly, existing behavior deviation detection methods often rely on simple rules and threshold judgments when dealing with behavioral differences between different companies, and lack comprehensive consideration of group characteristics and individual differences in corporate behavior, which easily leads to problems such as false positives and false negatives. Summary of the invention

[0004] In view of the problems of existing business information supervision technology in real-time dynamic supervision and risk assessment, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is how to timely identify potential business risks and automatically adjust regulatory rules through a dynamic rule engine.

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

[0007] In the first aspect, an embodiment of the present invention provides a method for dynamic supervision of business information based on big data, which includes collecting recent business activity data from different sources, and using a dynamic clustering algorithm to divide corporate behaviors into cluster groups according to characteristics, and identifying companies that deviate from normal behavior groups based on behavioral deviations; establishing a dynamically updated behavioral baseline model for each cluster group, and dynamically adjusting the baseline based on the latest data; based on the deviation and the behavioral baseline model, performing real-time risk assessment on the company's business behavior, and triggering graded warnings; based on the graded warning results, triggering the dynamic rule engine to automatically adjust the supervision rules.

[0008] As a preferred solution of the method for dynamic supervision of business information based on big data described in the present invention, the method of using a dynamic clustering algorithm to cluster corporate behaviors includes the following steps: using a dynamic clustering algorithm to group companies according to their business behaviors, and the calculation formula is as follows:

[0009]

[0010] Among them, d c represents the Euclidean distance between the i-th enterprise and the j-th cluster group, x ik is the kth eigenvalue of the ith enterprise, μ jk is the kth eigenvalue of the jth cluster group, and n is the number of feature dimensions.

[0011] As a preferred solution of the method for dynamic supervision of business information based on big data described in the present invention, the identification of enterprises that deviate from the normal behavior group based on the behavior deviation degree includes the following steps: calculating the deviation degree between the enterprise behavior and the cluster center to which it belongs, and identifying abnormal behavior; the formula for the deviation degree is:

[0012]

[0013] Among them, PD i is the deviation of the i-th enterprise, σ j is the standard deviation of the cluster group; when PD i >When the deviation threshold is set, the companies involved will be marked as having potential risks.

[0014] As a preferred solution of the method for dynamic supervision of business information based on big data described in the present invention, the establishment of a dynamically updated behavioral baseline model and the dynamic adjustment of the baseline according to the latest data include: extracting the characteristic values ​​of the clustering group from the behavioral data of each clustering group; establishing a preliminary behavioral baseline model for each clustering group, using a weighted average method, and considering the linear and nonlinear contributions of each feature; comparing the enterprise data in the clustering group with the corresponding behavioral baseline values, and calculating the difference of each enterprise in the clustering group; if the differences of multiple enterprises in a clustering group exceed the difference threshold, the behavioral baseline model of the clustering group is automatically adjusted dynamically, and the behavioral baseline value of the group is recalculated until the final behavioral baseline model is determined.

[0015] As a preferred solution of the method for dynamic supervision of business information based on big data described in the present invention, the preliminary behavior baseline model includes:

[0016]

[0017] Among them, δ jis the behavioral benchmark value of the jth cluster group, ω ij is the weight of the i-th enterprise in the j-th cluster group, N j is the number of enterprises in the jth cluster group, α and β are weight coefficients, which control the influence of the linear and nonlinear parts of the characteristics respectively.

[0018] As a preferred solution of the method for dynamic supervision of business information based on big data described in the present invention, the difference degree is calculated as follows:

[0019]

[0020] Among them, D ij is the difference between the baseline model of the behavior of the i-th enterprise and the j-th cluster group, σ jk is the standard deviation of the kth feature of the jth cluster group, δ jk is the baseline value of the kth feature in the jth cluster group.

[0021] As a preferred solution of the method for dynamic supervision of business information based on big data described in the present invention, the real-time risk assessment of the business behavior of the enterprise and the triggering of graded warnings include the following steps: according to the final behavioral baseline model, when the difference of the enterprise exceeds the set difference threshold, the enterprise involved is marked; the enterprise marked in the first round of calculation of deviation and difference is given a preliminary warning prompt to prompt relevant personnel to pay attention; the risk status of the marked enterprise is re-evaluated in subsequent continuous cycles. If the deviation and difference of the same enterprise in the second round of calculation exceed the difference threshold again, it is considered that the risk of the enterprise is continuous or serious; according to the continuity of the enterprise's behavior and the severity of the deviation, the risk warning level is gradually upgraded.

[0022] In the second aspect, an embodiment of the present invention provides a dynamic business information supervision system based on big data, which includes a data collection and clustering module, which is used to collect recent business activity data from different sources, and use a dynamic clustering algorithm to group corporate behaviors in real time according to characteristics, and identify companies that deviate from normal behavior groups based on behavioral deviations; a behavior baseline model construction module, which is used to establish a dynamically updated behavior baseline model for each cluster group, and dynamically adjust the baseline based on the latest data; a risk assessment and graded warning module, which is used to perform real-time risk assessment on the company's business behavior based on deviations and behavior baseline models, and trigger graded warnings; a supervision rule adjustment module, which is used to trigger the dynamic rule engine to automatically adjust the supervision rules according to the graded warning results.

[0023] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the method for dynamic supervision of business information based on big data as described in the first aspect of the present invention are implemented.

[0024] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the method for dynamic supervision of business information based on big data as described in the first aspect of the present invention are implemented.

[0025] The beneficial effects of the present invention are as follows: the present invention adopts a dynamic clustering algorithm to group corporate behaviors in real time, identifies abnormal behavior companies according to the degree of behavior deviation, and establishes a dynamically updated behavior baseline model based on group behavior characteristics, which can adjust the benchmark according to the latest data, solving the problem that the prior art cannot respond to changes in real time and cannot accurately identify abnormal corporate behaviors; and the present invention can timely identify potential business risks through real-time risk assessment and graded early warning mechanism, and automatically adjust regulatory rules through a dynamic rule engine, thereby improving the adaptability and response speed of the regulatory system. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 The figure is a flow chart of the dynamic supervision method of business information based on big data.

[0028] Figure 2 This is a structural diagram of the dynamic supervision system of business information based on big data. DETAILED DESCRIPTION

[0029] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0030] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0031] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0032] Example 1

[0033] Reference Figure 1-2 , which is the first embodiment of the present invention, and provides a method for dynamic supervision of business information based on big data, including:

[0034] S1: Collect recent business activity data from different sources, and use dynamic clustering algorithms to divide corporate behaviors into cluster groups according to their characteristics, and identify companies that deviate from normal behavior groups based on their behavioral deviations.

[0035] Specifically, business activity data is collected from multiple recent sources (such as corporate financial systems, sales records, market transaction data, network monitoring, etc.), where data types include structured data (such as numerical data) and unstructured data (such as text descriptions, log data).

[0036] It should be noted that in order to cope with the rapid changes in market updates and reforms, the collection cycle is set during the data collection stage to ensure that it can adapt to dynamic changes and obtain the most representative data in real time. The collection cycle can be flexibly set according to market dynamics, corporate changes, seasonal fluctuations or other relevant factors. For example, the sales pattern of a company may fluctuate significantly during holidays or promotions, so the data collection cycle can be shortened during these special periods to ensure that changes are captured in a timely manner.

[0037] The collected data is cleaned and normalized, and data from different sources are formatted in a unified manner.

[0038] Furthermore, key features such as sales fluctuations, transaction frequency, and customer complaints are extracted from the data, and feature selection algorithms such as principal component analysis (PCA) are applied to reduce the data dimensionality and highlight the most important features.

[0039] Use a dynamic clustering algorithm to group enterprises according to their business behaviors. The calculation formula is as follows:

[0040]

[0041] Among them, d c represents the Euclidean distance between the i-th enterprise and the j-th cluster group, x ik is the kth eigenvalue of the ith enterprise in cluster group j, μ jkis the kth eigenvalue of the jth cluster group, and n is the number of feature dimensions, that is, the number of features described for each enterprise in the clustering algorithm.

[0042] It should be noted that the Euclidean distance here refers to the distance between the center of the cluster group and the enterprise.

[0043] Furthermore, the deviation between the enterprise behavior and its cluster center is calculated to identify behavioral anomalies, where the deviation formula is:

[0044]

[0045] Among them, PD i is the deviation of the i-th enterprise, σ j is the standard deviation of the jth cluster group; when PD i >When the deviation threshold is set, the companies involved will be marked as having potential risks.

[0046] S2: Establish a dynamically updated behavioral baseline model for each cluster group, and dynamically adjust the baseline based on the latest data to ensure that the behavioral baseline model is synchronized with the actual operating conditions.

[0047] S2.1: Extract the characteristic values ​​of the cluster group from the behavioral data of each cluster group obtained in S1, such as average sales, average transaction frequency, and average customer satisfaction. By extracting group features based on cluster groups rather than single corporate behaviors, the stability and representativeness of the baseline are further enhanced, and it can adapt to the dynamic changes of different groups.

[0048] S2.2: Establish a preliminary behavioral baseline model for each cluster group, using the weighted average method and considering the linear and nonlinear contributions of each feature.

[0049] Preferably, the preliminary behavioral baseline model is:

[0050]

[0051] Among them, δ j is the behavioral benchmark value of the jth cluster group, ω ij is the weight of the i-th enterprise in the j-th cluster group, N j is the number of enterprises in the jth cluster group, α and β are weight coefficients, which control the influence of the linear and nonlinear parts of the characteristics respectively.

[0052] S2.3: Compare the enterprise data with the behavioral benchmark value and calculate the difference of each enterprise in the cluster group. The difference calculation formula is as follows:

[0053]

[0054] Among them, D ij is the difference between the baseline model of the behavior of the i-th enterprise and the j-th cluster group, σ jk is the standard deviation of the kth feature of the jth cluster group, δ jk is the baseline value of the kth feature in the jth cluster group.

[0055] Among them, the enterprise data compared with the behavioral baseline model is data within the same period or data within a similar period.

[0056] S2.4: If the differences among multiple enterprises exceed the set threshold, the behavioral baseline model of the cluster group is automatically adjusted dynamically and the baseline value of the group is recalculated.

[0057] By comparing the adaptability of the behavioral baseline model to enterprise data before and after the update, the effectiveness of the update can be verified. If the updated behavioral baseline model cannot better adapt to the current data, roll back to the original baseline.

[0058] S3: Based on the deviation and behavioral baseline model, conduct real-time risk assessment of the company's business behavior and trigger graded warnings.

[0059] Preferably, the real-time data of enterprise behaviors are compared according to the updated behavioral baseline model in S2.4 to identify enterprises with higher differences.

[0060] The difference is determined by the aforementioned calculation formula and compared with the warning threshold. That is, when the difference of an enterprise exceeds the set difference threshold, the enterprise involved is marked and considered to have potential risks.

[0061] Furthermore, during real-time risk assessment, the operations of marking the enterprises involved and conducting graded warnings are divided into the following steps:

[0062] For enterprises that were marked in the first round of calculation of deviation and difference, preliminary early warning reminders will be issued to prompt relevant personnel to pay attention. At this time, the enterprise is in the observation period and needs further monitoring;

[0063] The risk status of the marked enterprises is re-evaluated in subsequent consecutive cycles. If the deviation and difference of the same enterprise in the second round of calculations exceed the difference threshold again, it can be considered that the risk of the enterprise is more persistent or serious.

[0064] Depending on the persistence of the company's behavior and the severity of the deviation, the risk warning level will be gradually upgraded from "low risk" to "high risk".

[0065] S4: Based on the graded warning results, the dynamic rule engine is triggered to automatically adjust the regulatory rules and optimize subsequent data processing and analysis strategies to adapt to the newly identified risk types.

[0066] Collect the warning information output from the S3 stage, including the company's warning level, risk level, and number of flags, and compare the warning data of the current cycle with the historical cycle to identify emerging risk patterns. For example, if the frequency of a certain type of enterprise increases significantly (such as a specific behavior pattern in a certain industry becomes more prominent), then this pattern needs to become part of the new regulatory rules.

[0067] Defining new regulatory rules includes: adjusting existing rules or designing new rules based on newly identified risk types. For example, new difference thresholds can be set, or new feature dimensions can be added to the behavioral baseline model; such as adding new regulatory parameters such as "seasonal fluctuations", "market trend changes", and "industry instability", and expanding existing data processing rules.

[0068] Furthermore, this embodiment also provides a big data-based business information dynamic supervision system, including:

[0069] The data collection and clustering module is used to collect recent business activity data from different sources, and use dynamic clustering algorithms to group corporate behaviors in real time according to their characteristics, and identify companies that deviate from the normal behavior group based on the degree of behavioral deviation.

[0070] The behavior baseline model building module is used to build a dynamically updated behavior baseline model for each cluster group and dynamically adjust the baseline based on the latest data;

[0071] The risk assessment and graded warning module is used to conduct real-time risk assessment of the company's business behavior based on the deviation and behavioral baseline model, and trigger graded warnings.

[0072] The regulatory rule adjustment module is used to trigger the dynamic rule engine to automatically adjust the regulatory rules according to the graded warning results.

[0073] This embodiment also provides a computer device, which is suitable for the case of a dynamic supervision method of business information based on big data, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the dynamic supervision method of business information based on big data as proposed in the above embodiment.

[0074] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0075] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for dynamic supervision of business information based on big data as proposed in the above embodiment is implemented.

[0076] In summary, the present invention adopts a dynamic clustering algorithm to group corporate behaviors in real time, identifies abnormal behavior companies according to the degree of behavior deviation, and establishes a dynamically updated behavior baseline model based on group behavior characteristics, which can adjust the benchmark according to the latest data, solving the problem that the prior art cannot respond to changes in real time and cannot accurately identify abnormal corporate behaviors; and the present invention can timely identify potential business risks through real-time risk assessment and graded early warning mechanism, and automatically adjust regulatory rules through a dynamic rule engine, thereby improving the adaptability and response speed of the regulatory system.

[0077] Example 2

[0078] Reference Figure 1 , which is the second embodiment of the present invention, and this embodiment provides a method for dynamic supervision of business information based on big data. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0079] The experiment selected 50 enterprises in a certain economic zone as samples, covering enterprises in different industries, including retail, manufacturing, and services. The goal was to identify enterprises that deviate from normal business operations and issue risk warnings through dynamic clustering algorithms and real-time deviation detection.

[0080] First, experimental data is collected from multiple channels, including the company's financial system, sales records, customer feedback, market transaction data, and online public opinion data. The data types include structured data (such as sales, transaction volume, etc.) and unstructured data (such as customer complaints, social media comments, etc.). The collection cycle is set to once a month, but it is adjusted to once a week during holidays and promotions to ensure that short-term fluctuations can be captured in a timely manner.

[0081] After data collection, it is first cleaned and normalized. All data is converted into a standard format, numerical data is normalized, and text data is converted into structured features through natural language processing (NLP) algorithms to facilitate subsequent analysis. Then, principal component analysis (PCA) is used for feature selection to extract key information including sales fluctuations, transaction frequency, customer satisfaction, etc., to reduce data dimensions and improve the efficiency of cluster analysis.

[0082] After feature extraction is completed, a dynamic clustering algorithm is used to group enterprises. The distance between an enterprise and its cluster center is calculated using the Euclidean distance to determine whether it deviates from the normal behavior of the group. By calculating the deviation, the deviation threshold is set to more than 3 times the standard deviation, and the enterprise is marked as a high-risk enterprise. Based on these cluster groups and deviation results, a dynamically updated behavioral baseline model is constructed and adjusted according to real-time data. The baseline model of the enterprise group is updated monthly to ensure that it adapts to changes in the market and corporate behavior.

[0083] In the early warning stage, risk assessment models are used to analyze corporate behavior, mark companies with high deviations and trigger early warnings. Early warnings are divided into three levels: low risk, medium risk and high risk. Low-risk companies need to be kept under attention, while high-risk companies need to be intervened immediately. Finally, based on the early warning results, the dynamic rule engine is triggered to adjust the regulatory rules, such as adjusting the difference threshold, introducing new market factors, etc.

[0084] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for dynamic supervision of business information based on big data, characterized by: include, Collect recent business activity data from different sources, and use dynamic clustering algorithms to divide corporate behaviors into cluster groups, and identify companies that deviate from normal behavior groups based on their behavioral deviations; Establish a dynamically updated behavioral baseline model for each cluster group and dynamically adjust the baseline based on the latest data; Based on the deviation and the behavior baseline model, a real-time risk assessment is performed on the business behavior of the enterprise, and a graded warning is triggered; Based on the graded warning results, the dynamic rule engine is triggered to automatically adjust the regulatory rules.

2. The method for dynamic supervision of business information based on big data as claimed in claim 1, characterized in that: The method of using a dynamic clustering algorithm to divide corporate behaviors into cluster groups includes the following steps: Use a dynamic clustering algorithm to group enterprises according to their business behaviors. The calculation formula is as follows: Among them, d c represents the Euclidean distance between the i-th enterprise and the j-th cluster group, x ik is the kth eigenvalue of the ith enterprise, μ jk is the kth eigenvalue of the jth cluster group, and n is the number of feature dimensions.

3. The method for dynamic supervision of business information based on big data as claimed in claim 2, characterized in that: The method of identifying enterprises that deviate from normal behavior groups according to the degree of behavior deviation comprises the following steps: Calculate the deviation between the enterprise behavior and the cluster center to which it belongs, and identify behavioral anomalies; The formula for the deviation is: Among them, PD i is the deviation of the i-th enterprise, σ j is the standard deviation of the cluster group; when PD i >When the deviation threshold is set, the companies involved will be marked as having potential risks.

4. The method for dynamic supervision of business information based on big data as claimed in claim 3, characterized in that: The step of establishing a dynamically updated behavioral baseline model and dynamically adjusting the baseline according to the latest data includes: Extracting characteristic values ​​of cluster groups from the behavioral data of each cluster group; Establish a preliminary behavioral baseline model for each cluster group, using the weighted average method and considering the linear and nonlinear contributions of each feature; Compare the enterprise data in the cluster group with the corresponding behavioral benchmark value, and calculate the difference degree of each enterprise in the cluster group; If the differences between multiple enterprises in a cluster group exceed the difference threshold, the behavioral baseline model of the cluster group is automatically adjusted dynamically, and the behavioral baseline value of the group is recalculated until the final behavioral baseline model is determined.

5. The method for dynamic supervision of business information based on big data as claimed in claim 4, characterized in that: The preliminary behavioral baseline model includes: Among them, δ j is the behavioral baseline value of the jth cluster group, ω ij is the weight of the i-th enterprise in the j-th cluster group, N j is the number of enterprises in the jth cluster group, α and β are weight coefficients, which control the influence of the linear and nonlinear parts of the characteristics respectively.

6. The method for dynamic supervision of business information based on big data as claimed in claim 5, characterized in that: The difference is calculated as follows: Among them, D ij is the difference between the baseline model of the behavior of the i-th enterprise and the j-th cluster group, σ jk is the standard deviation of the kth feature of the jth cluster group, δ jk is the baseline value of the kth feature in the jth cluster group.

7. The method for dynamic supervision of business information based on big data according to claim 6, characterized in that: The real-time risk assessment of the business operations of the enterprise and triggering of graded warnings include the following steps: According to the final behavioral baseline model, when the difference of an enterprise exceeds the set difference threshold, the enterprise involved will be marked; Issue preliminary warnings to enterprises that were marked in the first round of calculation of deviation and difference, prompting relevant personnel to pay attention; The risk status of the marked enterprises will be reassessed in subsequent consecutive cycles. If the deviation and difference of the same enterprise in the second round of calculations exceed the difference threshold again, the risk of the enterprise will be considered to be persistent or serious; The risk warning level will be gradually upgraded based on the persistence of the company's behavior and the severity of the deviation.

8. A system for dynamic supervision of business information based on big data, based on the method for dynamic supervision of business information based on big data according to any one of claims 1 to 7, characterized in that: Also includes, The data collection and clustering module is used to collect recent business activity data from different sources, and use dynamic clustering algorithms to group corporate behaviors in real time according to their characteristics, and identify companies that deviate from the normal behavior group based on their behavioral deviation; The behavior baseline model building module is used to build a dynamically updated behavior baseline model for each cluster group and dynamically adjust the baseline based on the latest data; The risk assessment and graded warning module is used to conduct real-time risk assessment of the enterprise's business behavior based on the deviation degree and behavioral baseline model, and trigger graded warnings; The regulatory rule adjustment module is used to trigger the dynamic rule engine to automatically adjust the regulatory rules according to the graded warning results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for dynamic supervision of business information based on big data described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for dynamic supervision of business information based on big data described in any one of claims 1 to 7 are implemented.

Images