Data analysis and control method and system applied to financial credit creation

Abstract

The invention discloses a data analysis and control method and system applied to financial credit and creativity, and the method comprises the steps: carrying out the data cleaning and data preprocessing of financial data, and obtaining the preprocessed financial data information; carrying out financial data category division based on the preprocessed financial data information, constructing a plurality of financial data topic domain sets through attribute features of each financial data category, carrying out correlation analysis, and constructing a financial database in combination with the financial data topic domain sets and correlation analysis results; performing importance evaluation on each financial data subject domain in the financial database, associating different importance levels with corresponding use permissions, and performing data encryption on each financial data subject domain; and constructing a financial service management and control model, analyzing the real-time query demand and the required authority of the target user, performing risk assessment on the target user, and analyzing whether the current query demand needs to be managed and controlled. Therefore, the security of financial data and the intelligence of management are improved.

Description

Technical Field

[0001] The present invention relates to the field of financial information innovation technology, and in particular to a data analysis and control method and system applied to financial information innovation. Background Art

[0002] With the advancement of financial information innovation policies, the financial industry's demand for independent innovation technology continues to increase. The core of financial information innovation lies in building an independent and controllable information technology system to ensure the security, compliance and intelligent level of data management of financial data. In this context, financial institutions not only need a safe and reliable underlying infrastructure, but also intelligent data analysis and control methods to achieve efficient management, analysis and real-time risk control of data. Traditional financial data analysis methods usually rely on rules or statistical analysis based on historical data, which cannot quickly respond to dynamic market environments and changes in user behavior. At the same time, only evaluating a single user behavior pattern leads to inefficient risk control, which is insufficient in the face of increasingly complex financial risks and compliance requirements.

[0003] Therefore, how to better analyze and control financial data and intelligently identify the regular and abnormal behaviors of different types of users to improve the security of financial data and the intelligence of management is an urgent problem to be solved. Summary of the invention

[0004] The present invention overcomes the defects of the prior art and provides a data analysis and control method and system applied to financial information innovation, whose important purpose is to improve the effectiveness, security and intelligence of financial data management.

[0005] To achieve the above-mentioned purpose, the present invention provides a data analysis and control method applied to financial information innovation in the first aspect, including: Acquiring financial data, performing data cleaning on the financial data, and performing data preprocessing on the cleaned financial data to obtain preprocessed financial data information; Based on the pre-processed financial data information, financial data categories are divided, several financial data subject domain sets are constructed through attribute characteristics of each financial data category, and correlation analysis is performed, and a financial database is constructed by combining the financial data subject domain sets and the correlation analysis results; Performing importance evaluation on each financial data subject domain in the financial database, associating different importance levels with corresponding usage permissions, and encrypting data on each financial data subject domain according to the evaluation results; Build a financial service management and control model, analyze the real-time query needs of target users and determine the required permissions to generate required permission information, conduct risk assessment on target users based on the required permission information, and analyze whether the current query needs need to be controlled.

[0006] In this solution, the financial data is obtained, the financial data is cleaned, and data preprocessing is performed on the cleaned financial data to obtain preprocessed financial data information, which specifically includes: Acquire financial data stored in a database, perform data cleaning on the acquired financial data, and calculate the data standard deviation of the cleaned financial data; The calculated data standard deviation is compared with the preset standard deviation range, and the data corresponding to the data standard deviation that is not within the preset standard deviation range is defined as an outlier, and the outlier is eliminated and the difference is compensated; The financial data after outlier elimination and difference compensation are standardized, and pre-processed financial data information is generated based on the standardized financial data.

[0007] In this solution, the financial data classification is performed based on the pre-processed financial data information, several financial data subject domain sets are constructed through the attribute characteristics of each financial data category and correlation analysis is performed, and a financial database is constructed by combining the financial data subject domain sets and the correlation analysis results, specifically including: Acquire preprocessed financial data information, perform feature extraction on the preprocessed financial data information, and perform feature construction and generate a feature matrix based on the extracted financial data feature information using feature coding; The K-means fuzzy clustering algorithm is introduced, the number of cluster centers is preset, the Euclidean distance from each feature matrix to each cluster center is calculated, and the Euclidean distance from each feature matrix to each cluster center is sorted; The minimum Euclidean distance value from the target feature matrix to each cluster center is selected through the sorting results, and the cluster center corresponding to the minimum Euclidean distance value is used as the cluster center of the target feature matrix and several clusters are output to obtain the initial category division information; Extracting attribute features of each category of financial data including data source, data type and data usage based on the initial category classification information, and performing word segmentation according to the extracted attribute features to obtain corresponding word vectors; The word vectors are weighted averaged to construct a sentence vector expression, and the frequency and distribution breadth of the word vectors in the extracted attribute features are obtained, and the word vectors that meet the preset standards are selected as the description keyword vectors; Based on the descriptive keyword vector, several financial data subject domain sets are constructed, the correlation between each financial data subject and the set is obtained through Spearman correlation analysis, the first analysis information is obtained, and a financial database is constructed according to the financial data subject domain set and the first analysis information.

[0008] In this solution, the importance of each financial data subject domain in the financial database is evaluated, and different importance levels are associated with corresponding usage permissions. Data encryption is performed on each financial data subject domain according to the evaluation results, specifically including: Acquire a financial database, construct a materiality assessment rule, perform a materiality assessment on each financial data subject domain in the financial database, and obtain materiality assessment information; Preset a number of importance level threshold ranges, associate different importance levels with corresponding usage permissions, and judge the importance assessment information against the preset importance level threshold ranges; The importance level of each financial data subject domain is defined according to the judgment result, and data encryption is performed based on the usage rights corresponding to the importance level of each financial data subject domain.

[0009] In this solution, the financial service management and control model is constructed to analyze the real-time query needs of target users and determine the required permissions to generate required permission information, specifically including: Obtaining the first analysis information and the importance level and usage authority corresponding to each financial data subject domain, constructing a subject domain association graph using the correlation between each financial data subject domain, and using the corresponding importance level and usage authority as subsidiary features; Constructing a financial service management and control model using a graph neural network, training the financial service management and control model using a financial database and the subject domain association graph, saving model parameters after training, and outputting a financial service management and control model that meets expectations; Obtaining user query information, encoding the user query information to obtain a user query feature vector, generating user demand information according to the user query feature vector, and inputting the information into the financial service management and control model for analysis; Determine the category information of the financial data or financial service queried by the user based on the input user demand information, extract the usage rights of the corresponding demand financial data or service according to the category information, and generate demand authority information; Obtain the user's identity and permissions, perform matching analysis with the required permission information, determine whether the target user can use the corresponding financial data or financial services based on the analysis results, and conduct risk assessment on the target user.

[0010] In this solution, the target user is risk assessed based on the required permission information to analyze whether the current query demand needs to be managed, specifically including: If the matching analysis result shows that the target user can use the required financial data or financial services, the target user's historical query information is obtained, and a risk assessment is performed on the target user's current financial data or financial service request; Extracting features of the target user's historical query information, extracting the target user's historical query features, including query frequency features, query content features, query behavior features, and request permission features, to obtain historical query feature information; Building a historical query profile of the target user based on the historical query feature information, building a risk assessment model using an isolation forest algorithm, and inputting the historical query profile of the target user into the risk assessment model for training; Obtaining the required authority information and the user query information, inputting them into the risk assessment model, generating a real-time profile of the target user's query request based on the input required authority information and the user query information, performing risk score calculation, and outputting the risk score; The risk assessment is the degree of deviation between the real-time profile of the target user's query request and the historical query profile of the target user. A risk level threshold is preset, and the risk score is judged against the risk level threshold to generate risk assessment result information; A query request feedback instruction is generated according to the risk assessment result information to control the query request behavior of the target user.

[0011] A second aspect of the present invention provides a data analysis and control system applied to financial information innovation, the system comprising: a memory, a processor, the memory containing a data analysis and control method program applied to financial information innovation, the data analysis and control method program applied to financial information innovation being executed by the processor to implement the following steps: Acquiring financial data, performing data cleaning on the financial data, and performing data preprocessing on the cleaned financial data to obtain preprocessed financial data information; Based on the pre-processed financial data information, financial data categories are divided, several financial data subject domain sets are constructed through attribute characteristics of each financial data category, and correlation analysis is performed, and a financial database is constructed by combining the financial data subject domain sets and the correlation analysis results; Performing importance evaluation on each financial data subject domain in the financial database, associating different importance levels with corresponding usage permissions, and encrypting data on each financial data subject domain according to the evaluation results; Build a financial service management and control model, analyze the real-time query needs of target users and determine the required permissions to generate required permission information, conduct risk assessment on target users based on the required permission information, and analyze whether the current query needs need to be controlled.

[0012] The present invention discloses a data analysis and control method and system applied to financial information creation, including: data cleaning and data preprocessing of financial data to obtain preprocessed financial data information; classification of financial data based on preprocessed financial data information, constructing several financial data subject domain sets through attribute characteristics of each financial data category and performing correlation analysis, and constructing a financial database in combination with the financial data subject domain set and the correlation analysis result; evaluating the importance of each financial data subject domain in the financial database, and associating different importance levels with corresponding usage permissions, and encrypting data for each financial data subject domain; constructing a financial service control model, analyzing the real-time query needs and required permissions of target users, and performing risk assessment on target users, and analyzing whether the current query needs need to be controlled. Thus, the security of financial data and the intelligence of management are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the drawings required for use in the embodiments or exemplary descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to the drawings without paying creative work.

[0014] Figure 1 A flow chart of a data analysis and control method applied to financial information innovation provided by one embodiment of the present invention; Figure 2 A flow chart of a financial data management method provided by an embodiment of the present invention; Figure 3 A block diagram of a data analysis and control system applied to financial information innovation provided by an embodiment of the present invention; The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0015] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0016] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0017] Figure 1A flow chart of a data analysis and control method applied to financial information innovation provided by one embodiment of the present invention; like Figure 1 As shown, the present invention provides a flow chart of a data analysis and control method applied to financial information innovation, including: S102, acquiring financial data, performing data cleaning on the financial data, and performing data preprocessing on the cleaned financial data to obtain preprocessed financial data information; S104, classifying the financial data based on the pre-processed financial data information, constructing a number of financial data subject domain sets based on the attribute characteristics of each financial data category and performing correlation analysis, and constructing a financial database in combination with the financial data subject domain sets and the correlation analysis results; S106, evaluating the importance of each financial data subject domain in the financial database, associating different importance levels with corresponding usage permissions, and encrypting data in each financial data subject domain according to the evaluation results; S108, building a financial service management and control model, analyzing the real-time query needs of target users and determining the required permissions to generate required permission information, conducting a risk assessment on the target users based on the required permission information, and analyzing whether the current query needs need to be managed and controlled.

[0018] It should be noted that the present invention provides a data analysis and control method and system for financial information innovation, which ensures the accuracy and consistency of the data by cleaning and preprocessing the initial financial data. Then, based on the preprocessed financial data, the data is divided into several data sets using the K-means fuzzy clustering algorithm to obtain the initial classification information, that is, the various types of data are preliminarily divided into various categories. Subsequently, based on the attribute characteristics of each category of financial data, such as data source, data purpose, etc., the core semantic features of each category, that is, the content represented by each category of financial data, are further analyzed to construct several financial data subject domain sets, each subject domain set is represented by the key features of a certain type of financial data, and helps the system to classify and understand the data in multiple dimensions. At the same time, the correlation strength between the subject domain sets is analyzed, and then the potential relationship between the themes is clearly identified, and a financial database is constructed, and the permissions and data encryption are set for each financial data subject. Then, a financial service control model is constructed to analyze the real-time query needs of the target user and determine the required permissions, and to determine whether the real-time request behavior is risky and control it according to the user's required permissions. Thereby improving the security of financial data and the intelligence of management.

[0019] Furthermore, in a preferred embodiment of the first solution, the acquiring of financial data, performing data cleaning on the financial data, and performing data preprocessing on the cleaned financial data to obtain preprocessed financial data information specifically include: Acquire financial data stored in a database, perform data cleaning on the acquired financial data, and calculate the data standard deviation of the cleaned financial data; The calculated data standard deviation is compared with the preset standard deviation range, and the data corresponding to the data standard deviation that is not within the preset standard deviation range is defined as an outlier, and the outlier is eliminated and the difference is compensated; The financial data after outlier elimination and difference compensation are standardized, and pre-processed financial data information is generated based on the standardized financial data.

[0020] It should be noted that relevant financial data is obtained from the database, which usually contains multi-dimensional information such as transaction amount, transaction time, account information, etc. In order to ensure the accuracy and consistency of the data, the obtained financial data is cleaned to identify and deal with quality problems such as missing values, duplicate values ​​and erroneous values ​​in the data. After the data cleaning is completed, the system removes outliers from the cleaned financial data, removes samples that are significantly inconsistent with the expected distribution from the data set, and replaces the removed abnormal data by difference compensation. For example, the average value or interpolation method of neighboring data can be used to fill in the missing data, thereby maintaining the continuity and overall trend of the data. After the outlier removal and difference compensation are completed, the data is standardized. Data standardization is to convert data of different magnitudes into the same scale so that data of each dimension can be analyzed and compared under the same standard. Thereby improving the reliability and accuracy of financial data.

[0021] Furthermore, in a preferred embodiment of the first solution, the financial data classification is performed based on the pre-processed financial data information, a number of financial data subject domain sets are constructed through the attribute characteristics of each financial data category and correlation analysis is performed, and a financial database is constructed in combination with the financial data subject domain sets and the correlation analysis results, specifically including: Acquire preprocessed financial data information, perform feature extraction on the preprocessed financial data information, and perform feature construction and generate a feature matrix based on the extracted financial data feature information using feature coding; The K-means fuzzy clustering algorithm is introduced, the number of cluster centers is preset, the Euclidean distance from each feature matrix to each cluster center is calculated, and the Euclidean distance from each feature matrix to each cluster center is sorted; The minimum Euclidean distance value from the target feature matrix to each cluster center is selected through the sorting results, and the cluster center corresponding to the minimum Euclidean distance value is used as the cluster center of the target feature matrix and several clusters are output to obtain the initial category division information; Extracting attribute features of each category of financial data including data source, data type and data usage based on the initial category classification information, and performing word segmentation according to the extracted attribute features to obtain corresponding word vectors; The word vectors are weighted averaged to construct a sentence vector expression, and the frequency and distribution breadth of the word vectors in the extracted attribute features are obtained, and the word vectors that meet the preset standards are selected as the description keyword vectors; Based on the descriptive keyword vector, several financial data subject domain sets are constructed, the correlation between each financial data subject and the set is obtained through Spearman correlation analysis, the first analysis information is obtained, and a financial database is constructed according to the financial data subject domain set and the first analysis information.

[0022] It should be noted that the preprocessed financial data information is first subjected to feature extraction. The core features are extracted from the raw data in order to better understand and classify the internal structure of the data. After feature extraction, the extracted financial data features are constructed through feature encoding to generate a feature matrix containing each feature. Next, the K-means fuzzy clustering algorithm is introduced to group the feature matrix and output several clusters to obtain initial category division information, thereby distinguishing the characteristics of the financial data. Based on the initial category division information, the attribute characteristics of each category of financial data are further analyzed, including key information such as the source of the data, data type, and data usage. For these attribute features, the words related to the category are extracted through word segmentation technology, and word vectors are generated to represent the feature attributes. Subsequently, a sentence vector expression is generated by calculating the weighted average of the word vectors to generate a unified semantic representation for each category of data. At the same time, the frequency and distribution breadth of the word vector in each attribute feature are counted, and the qualified word vectors are screened out according to the preset standards and defined as description keyword vectors. The description keyword vector can represent the core semantic features of each category, making the subsequent analysis more accurate. A set of subject domains of several financial data is constructed based on the generated description keyword vectors. Each subject domain set is represented by the key features of a certain type of financial data, so that the data can be classified and understood in multiple dimensions. The relationship between each financial data subject is determined through Spearman correlation analysis, and the strength of association between subject sets is obtained, thereby clearly identifying the potential relationship between each subject. Finally, based on the financial data subject domain set and the first analysis information, the financial data is summarized and a financial database is constructed, making the financial data analysis more intelligent and adaptable.

[0023] Furthermore, in a preferred embodiment of the first solution, the importance of each financial data subject domain in the financial database is evaluated, and different importance levels are associated with corresponding usage permissions, and data encryption is performed on each financial data subject domain according to the evaluation result, specifically including: Acquire a financial database, construct a materiality assessment rule, perform a materiality assessment on each financial data subject domain in the financial database, and obtain materiality assessment information; Preset a number of importance level threshold ranges, associate different importance levels with corresponding usage permissions, and judge the importance assessment information against the preset importance level threshold ranges; The importance level of each financial data subject domain is defined according to the judgment result, and data encryption is performed based on the usage rights corresponding to the importance level of each financial data subject domain.

[0024] It should be noted that for data, the importance assessment rules are usually determined by combining factors such as the sensitivity of the data, the frequency of data use, the business scope involved, and the potential impact of the data on financial decisions. In this way, the criticality of different data is evaluated at the subject domain level to reflect the relative importance of different data. Subsequently, several importance level threshold ranges are set, and each importance level is associated with the corresponding usage permissions. The setting of the importance level threshold range ensures that data can be hierarchically controlled according to its importance, and different levels of data can be given different access rights to better protect sensitive information. After clarifying the importance level of each financial data subject domain, the corresponding usage permissions are further defined based on the importance level. These permissions include but are not limited to different access levels, operation permissions, or data viewing and processing permissions. At the same time, data of each importance level is appropriately encrypted to prevent access or leakage by unauthorized users. The encryption method varies depending on the importance level of the data. Data with higher importance adopts more complex and strict encryption methods to enhance security; data with relatively lower importance adopts conventional encryption methods to take into account efficiency. It effectively improves the security and compliance of financial data and realizes refined data management.

[0025] Further, in a preferred embodiment of the first solution, the construction of a financial service management and control model, analyzing the real-time query needs of target users and determining the required permissions to generate required permission information, specifically includes: Obtaining the first analysis information and the importance level and usage authority corresponding to each financial data subject domain, constructing a subject domain association graph using the correlation between each financial data subject domain, and using the corresponding importance level and usage authority as subsidiary features; Constructing a financial service management and control model using a graph neural network, training the financial service management and control model using a financial database and the subject domain association graph, saving model parameters after training, and outputting a financial service management and control model that meets expectations; Obtaining user query information, encoding the user query information to obtain a user query feature vector, generating user demand information according to the user query feature vector, and inputting the information into the financial service management and control model for analysis; Determine the category information of the financial data or financial service queried by the user based on the input user demand information, extract the usage rights of the corresponding demand financial data or service according to the category information, and generate demand authority information; Obtain the user's identity and permissions, perform matching analysis with the required permission information, determine whether the target user can use the corresponding financial data or financial services based on the analysis results, and conduct risk assessment on the target user.

[0026] It should be noted that the first analysis information and the importance level and corresponding usage rights of each financial data subject domain are first obtained. The importance level reflects the sensitivity and usage value of the data, while the usage rights define the access control scope of the data. A subject domain association graph is constructed to intuitively display the association structure between data subjects. This association graph presents the mutual relationship and dependency of each subject in the form of a network, and adds the importance level and usage rights of each subject domain as features in the graph structure. This feature addition helps the model to quickly identify the sensitivity and permission requirements of each subject when judging user permissions. A financial service management and control model is constructed using a graph neural network (GNN). The graph neural network can effectively process and learn the complex relationships in the subject domain association graph, making the model more intelligent in judging user request permissions and risk analysis. The model learns the association features, permission levels and usage conditions between data through repeated iterations, thereby ensuring that it has efficient and accurate judgment capabilities in actual use. When a user issues a query request, the query information is encoded to generate a feature vector of the user query. This feature vector represents the specific demand characteristics of the user's query. After inputting it into the financial service management and control model, the model determines the category of the specific financial data or service that the user is querying by analyzing the user's demand information, and extracts the corresponding data or service usage permissions based on the category, generates the required permission information, and thus clarifies the user's permission requirements in this request. To ensure the security and compliance of the query, the user's identity and currently assigned permissions are further obtained. The user's permission information is matched and analyzed with the generated required permission information to determine whether the target user is qualified to access the corresponding financial data or services. If the user's permissions do not meet the requirements, the request is rejected. If the user's permissions meet the requirements, a risk assessment is performed.

[0027] Furthermore, in a preferred embodiment of the first solution, the risk assessment of the target user is performed based on the required authority information to analyze whether the current query demand needs to be managed, specifically including: If the matching analysis result shows that the target user can use the required financial data or financial services, the target user's historical query information is obtained, and a risk assessment is performed on the target user's current financial data or financial service request; Extracting features of the target user's historical query information, extracting the target user's historical query features, including query frequency features, query content features, query behavior features, and request permission features, to obtain historical query feature information; Building a historical query profile of the target user based on the historical query feature information, building a risk assessment model using an isolation forest algorithm, and inputting the historical query profile of the target user into the risk assessment model for training; Obtaining the required authority information and the user query information, inputting them into the risk assessment model, generating a real-time profile of the target user's query request based on the input required authority information and the user query information, performing risk score calculation, and outputting the risk score; The risk assessment is the degree of deviation between the real-time profile of the target user's query request and the historical query profile of the target user. A risk level threshold is preset, and the risk score is judged against the risk level threshold to generate risk assessment result information; A query request feedback instruction is generated according to the risk assessment result information to control the query request behavior of the target user.

[0028] It should be noted that when the result of the matching analysis indicates that the target user can use the requested financial data or service, the target user's historical query information is further obtained to perform a risk assessment on the current request. By analyzing the historical query information, the system can extract multiple key features, including query frequency features, query content features, query behavior features, and request permission features. These historical query features can fully reflect the behavior patterns and usage habits of the target user, thereby forming the user's historical query feature information. After obtaining the historical query feature information, a historical query profile of the target user is constructed based on these features. This profile is not only a summary of the user's past query behavior, but also provides an important basis for subsequent risk assessment. Next, an isolation forest algorithm is used to construct a risk assessment model specifically for detecting anomalies in user query behavior. The target user's historical query profile is input into the risk assessment model for training to identify the user's normal query pattern. Subsequently, the required permission information and user query information are input into the trained risk assessment model, and a real-time profile of the target user's query request is generated based on the input data. The risk score of the user's current query request is calculated through the real-time profile. The score reflects the degree of deviation between the target user's real-time query behavior and its historical query profile. The greater the deviation, the more abnormal the current request is and the greater the risk. The generated risk score is compared with the preset risk level threshold to clarify whether the user's query request is within the acceptable risk range, thereby generating the corresponding risk assessment result information. If the risk score is higher than the preset threshold, the system will mark the request as high risk and take corresponding control measures. Finally, a query request feedback instruction is generated based on the risk assessment result information to control the query request behavior of the target user. Including measures such as restricting user access to specific financial data or services, requiring additional identity authentication, or directly rejecting requests, using dynamic risk assessment and control mechanisms to provide real-time protection for financial services and prevent potential security threats.

[0029] Figure 2 A flow chart of a financial data management method provided by an embodiment of the present invention; like Figure 2 As shown, the present invention provides a flow chart of a financial data management and control method, including: S202, obtaining user query information, encoding the user query information to obtain a user query feature vector and generating user demand information, and inputting the information into the financial service management and control model for analysis; S204, determining the category information of the financial data or financial service queried by the user based on the input user demand information, extracting the usage rights of the corresponding demand financial data or service according to the category information, and generating demand authority information; S206, obtaining the identity and authority of the user, performing matching analysis with the required authority information, and determining whether the target user can use the corresponding financial data or financial services according to the analysis result; S208, if the target user can use the corresponding financial data or financial services, obtaining the required authority information and the user query information, and inputting them into the risk assessment model for risk assessment; S210, based on the input required authority information and user query information, a real-time profile of the target user's query request is generated to calculate a risk score, and a risk score is output. According to the risk score, it is determined whether there is an abnormal risk, and the query request is managed and controlled.

[0030] In addition, in a data analysis and control method applied to financial information innovation provided by the present invention, the following steps are also included: Acquire historical query feature information of the target user, and perform time series processing on the historical query feature information to form a historical query feature time series sequence; The historical query feature time series is used as output, and the SARIMA model is used to analyze the historical habit patterns of the target user in using financial data or financial services to obtain historical habit pattern analysis information; Extracting request characteristics of the target user when making a request for financial data or financial services according to the historical habit regularity analysis information, including request frequency, request content, request address, and corresponding request time characteristics, to obtain first characteristic information; Based on the first feature information, a topology structure diagram is constructed with request content, request address and request time as the associated path, and the request frequency is associated with the topology structure diagram as an auxiliary feature to obtain a first topology structure diagram; Analyze the target user's preferred query behavior and content using the first topology diagram with the request frequency as the judgment indicator, set the trust level according to the request frequency corresponding to each query behavior and content, and construct a trust level score for the target user; When the target user makes the next query request, the trust score of the target user is adjusted according to the risk assessment result of the next query request of the target user. When the trust score of the target user is less than the preset threshold, the financial account of the target user is subject to risk control.

[0031] It should be noted that by analyzing the historical request habits of the target user, we can understand the services and data that the target user normally requests, and further use the types of services and data corresponding to their high-frequency and preferred requests to establish the target user's trust score. When the target user visits next time, if there is a deviation from his historical habits, his trust score will be adjusted. When it is adjusted to less than the preset threshold, the target user's account will be subject to risk management to avoid potential threats.

[0032] Figure 3 A data analysis and control system 3 applied to financial information innovation is provided in one embodiment of the present invention. The system includes: a memory 31 and a processor 32. The memory 31 contains a data analysis and control method program applied to financial information innovation. When the data analysis and control method program applied to financial information innovation is executed by the processor 32, the following steps are implemented: Acquiring financial data, performing data cleaning on the financial data, and performing data preprocessing on the cleaned financial data to obtain preprocessed financial data information; Based on the pre-processed financial data information, financial data categories are divided, several financial data subject domain sets are constructed through attribute characteristics of each financial data category, and correlation analysis is performed, and a financial database is constructed by combining the financial data subject domain sets and the correlation analysis results; Performing importance evaluation on each financial data subject domain in the financial database, associating different importance levels with corresponding usage permissions, and encrypting data on each financial data subject domain according to the evaluation results; Build a financial service management and control model, analyze the real-time query needs of target users and determine the required permissions to generate required permission information, conduct risk assessment on target users based on the required permission information, and analyze whether the current query needs need to be controlled.

[0033] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0034] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0035] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0036] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0037] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0038] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A data analysis and control method applied to financial information innovation, characterized in that: include: Acquiring financial data, performing data cleaning on the financial data, and performing data preprocessing on the cleaned financial data to obtain preprocessed financial data information; Based on the pre-processed financial data information, financial data categories are divided, several financial data subject domain sets are constructed through attribute characteristics of each financial data category, and correlation analysis is performed, and a financial database is constructed by combining the financial data subject domain sets and the correlation analysis results; Performing importance evaluation on each financial data subject domain in the financial database, associating different importance levels with corresponding usage permissions, and encrypting data on each financial data subject domain according to the evaluation results; Build a financial service management and control model, analyze the real-time query needs of target users and determine the required permissions to generate required permission information, conduct risk assessment on target users based on the required permission information, and analyze whether the current query needs need to be controlled.

2. According to claim 1, a data analysis and control method applied to financial information innovation is characterized in that: The acquiring of financial data, performing data cleaning on the financial data, and performing data preprocessing on the cleaned financial data to obtain preprocessed financial data information specifically includes: Acquire financial data stored in a database, perform data cleaning on the acquired financial data, and calculate the data standard deviation of the cleaned financial data; The calculated data standard deviation is compared with the preset standard deviation range, and the data corresponding to the data standard deviation that is not within the preset standard deviation range is defined as an outlier, and the outlier is eliminated and the difference is compensated; The financial data after outlier elimination and difference compensation are standardized, and pre-processed financial data information is generated based on the standardized financial data.

3. According to the data analysis and control method applied to financial information innovation according to claim 1, it is characterized in that: The method of classifying the financial data based on the pre-processed financial data information, constructing a plurality of financial data subject domain sets and performing correlation analysis based on the attribute characteristics of each financial data category, and constructing a financial database in combination with the financial data subject domain sets and the correlation analysis results specifically includes: Acquire preprocessed financial data information, perform feature extraction on the preprocessed financial data information, and perform feature construction and generate a feature matrix based on the extracted financial data feature information using feature coding; The K-means fuzzy clustering algorithm is introduced, the number of cluster centers is preset, the Euclidean distance from each feature matrix to each cluster center is calculated, and the Euclidean distance from each feature matrix to each cluster center is sorted; The minimum Euclidean distance value from the target feature matrix to each cluster center is selected through the sorting results, and the cluster center corresponding to the minimum Euclidean distance value is used as the cluster center of the target feature matrix and several clusters are output to obtain the initial category division information; Extracting attribute features of each category of financial data including data source, data type and data usage based on the initial category classification information, and performing word segmentation according to the extracted attribute features to obtain corresponding word vectors; The word vectors are weighted averaged to construct a sentence vector expression, and the frequency and distribution breadth of the word vectors in the extracted attribute features are obtained, and the word vectors that meet the preset standards are selected as the description keyword vectors; Based on the descriptive keyword vector, several financial data subject domain sets are constructed, the correlation between each financial data subject and the set is obtained through Spearman correlation analysis, the first analysis information is obtained, and a financial database is constructed according to the financial data subject domain set and the first analysis information.

4. According to claim 1, a data analysis and control method applied to financial information innovation is characterized in that: The step of evaluating the importance of each financial data subject domain in the financial database, associating different importance levels with corresponding usage permissions, and encrypting data in each financial data subject domain according to the evaluation results specifically includes: Acquire a financial database, construct a materiality assessment rule, perform a materiality assessment on each financial data subject domain in the financial database, and obtain materiality assessment information; Preset a number of importance level threshold ranges, associate different importance levels with corresponding usage permissions, and judge the importance assessment information against the preset importance level threshold ranges; The importance level of each financial data subject domain is defined according to the judgment result, and data encryption is performed based on the usage rights corresponding to the importance level of each financial data subject domain.

5. According to claim 1, a data analysis and control method applied to financial information innovation is characterized in that: The construction of the financial service management and control model analyzes the real-time query needs of the target user and determines the required permissions to generate the required permission information, specifically including: Obtaining the first analysis information and the importance level and usage authority corresponding to each financial data subject domain, constructing a subject domain association graph using the correlation between each financial data subject domain, and using the corresponding importance level and usage authority as subsidiary features; Constructing a financial service management and control model using a graph neural network, training the financial service management and control model using a financial database and the subject domain association graph, saving model parameters after training, and outputting a financial service management and control model that meets expectations; Obtaining user query information, encoding the user query information to obtain a user query feature vector, generating user demand information according to the user query feature vector, and inputting the information into the financial service management and control model for analysis; Determine the category information of the financial data or financial service queried by the user based on the input user demand information, extract the usage rights of the corresponding demand financial data or service according to the category information, and generate demand authority information; Obtain the user's identity and permissions, perform matching analysis with the required permission information, determine whether the target user can use the corresponding financial data or financial services based on the analysis results, and conduct risk assessment on the target user.

6. According to claim 1, a data analysis and control method applied to financial information innovation is characterized in that: The risk assessment of the target user according to the required authority information is performed to analyze whether the current query demand needs to be controlled, specifically including: If the matching analysis result shows that the target user can use the required financial data or financial services, the target user's historical query information is obtained, and a risk assessment is performed on the target user's current financial data or financial service request; Extracting features of the target user's historical query information, extracting the target user's historical query features, including query frequency features, query content features, query behavior features, and request permission features, to obtain historical query feature information; Building a historical query profile of the target user based on the historical query feature information, building a risk assessment model using an isolation forest algorithm, and inputting the historical query profile of the target user into the risk assessment model for training; Obtaining the required authority information and the user query information, inputting them into the risk assessment model, generating a real-time profile of the target user's query request based on the input required authority information and the user query information, performing risk score calculation, and outputting the risk score; The risk assessment is the degree of deviation between the real-time profile of the target user's query request and the historical query profile of the target user. A risk level threshold is preset, and the risk score is judged against the risk level threshold to generate risk assessment result information; Generate a query request feedback instruction based on the risk assessment result information to control the query request behavior of the target user.

7. A data analysis and control system applied to financial information innovation, characterized in that: The system includes: a memory and a processor, wherein the memory contains a data analysis and control method program applied to financial information innovation, and when the data analysis and control method program applied to financial information innovation is executed by the processor, the following steps are implemented: Acquiring financial data, performing data cleaning on the financial data, and performing data preprocessing on the cleaned financial data to obtain preprocessed financial data information; Based on the pre-processed financial data information, financial data categories are divided, several financial data subject domain sets are constructed through attribute characteristics of each financial data category, and correlation analysis is performed, and a financial database is constructed by combining the financial data subject domain sets and the correlation analysis results; Performing importance evaluation on each financial data subject domain in the financial database, associating different importance levels with corresponding usage permissions, and encrypting data on each financial data subject domain according to the evaluation results; Build a financial service management and control model, analyze the real-time query needs of target users and determine the required permissions to generate required permission information, conduct risk assessment on target users based on the required permission information, and analyze whether the current query needs need to be controlled.

Images