Business index management method and system of financial product, and electronic equipment

Abstract

The invention discloses a business index management method and system of a financial product and electronic equipment, and relates to the field of financial science and technology, and the method comprises the steps: extracting a product name of a newly-added financial product from a product newly-adding request; analyzing semantics of product names by utilizing a lightweight text classification model, outputting a product level recommendation directory based on semantic information of the product names and level constraint rules, and extracting key business indexes associated with newly added financial products in a target product tree by adopting a natural language model; mapping the key business indexes to a field recommendation model, querying field data of the data lake table by the field recommendation model, and outputting recommended fields; and storing a mapping relationship between the key business indexes and the recommendation fields into the target knowledge base. The technical problem that in the financial product information management process in the related technology, a key business index and a data table in a bottom layer data lake lack an association mechanism, and data islands are easily caused is solved.

Description

Technical Field

[0001] This invention relates to the field of financial technology or other related fields, and more specifically, to a method and system for managing business indicators of financial products, and electronic equipment. Background Technology

[0002] In modern financial operations, with the increasing diversification and complexity of financial products, managing product information and key business indicators, as well as real-time monitoring and risk warning of these indicators, has become a crucial issue for improving service quality and reducing operational risks. Currently, most financial institutions rely on manual processing and independent subsystem architectures for product management and business indicator monitoring. This approach has significant drawbacks: financial product information is scattered across various independent subsystems, such as credit, wealth management, and insurance systems. These subsystems maintain their own product trees and key business indicators, making it difficult for business personnel to obtain a unified view of all bank-wide products, impacting the efficiency and quality of product analysis and decision-making. Simultaneously, key business indicators lack an effective automatic correlation mechanism with the underlying data lake tables. The large amount of raw and processed data stored in the data lake cannot be directly mapped to business indicators, creating data silos. Cross-table analysis and data traceability face significant challenges, affecting the depth and breadth of data analysis.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a business indicator management method, system, and electronic device for financial products, which at least solves the technical problem in the related technology that the lack of a correlation mechanism between key business indicators and data tables in the underlying data lake during the information management process of financial products easily leads to data silos.

[0005] To achieve the above objectives, according to one aspect of this application, a method for managing business indicators of financial products is provided, comprising: receiving a product addition request from a user terminal; extracting the product name of the new financial product from the product addition request; analyzing the semantics of the product name using a lightweight text classification model; outputting a product-level recommendation directory based on the semantic information of the product name and hierarchical constraint rules, wherein the product-level recommendation directory includes the target hierarchical position of the new financial product in a target product tree; extracting key business indicators associated with the new financial product in the target product tree using a natural language model; mapping the key business indicators to a field recommendation model; querying field data from a data lake table using the field recommendation model; and outputting recommended fields; and storing the mapping relationship between the key business indicators and the recommended fields in a target knowledge base.

[0006] Optionally, the step of querying field data from the data lake table using the field recommendation model and outputting recommended fields includes: analyzing the indicator name and indicator description text of the key business indicator using the field recommendation model to obtain indicator semantic information; calculating the similarity between the key business indicator and the field names, annotation information, and inter-table relationships of each field in the data lake table based on the indicator semantic information; filtering out multiple fields with similarity greater than a preset similarity threshold to obtain the recommended fields; establishing a mapping relationship between the key business indicator and the recommended fields, and outputting the recommended fields.

[0007] Optionally, the field recommendation model is pre-built. Building the field recommendation model includes: constructing a node feature matrix and an adjacency matrix based on the description document, historical mapping relationship, and associated business terms for each business indicator; wherein the node feature matrix includes feature vectors of multiple nodes, and the adjacency matrix includes connection relationships between multiple nodes; the nodes are used to represent business indicators; constructing a graph attention network model based on the node feature matrix and the adjacency matrix; and establishing a mapping relationship between each node and a business term in the graph attention network model to generate the field recommendation model.

[0008] Optionally, the target product tree is pre-built, and the built target product tree includes: a first-level theme directory, including multiple financial themes; a second-level business directory, including multiple financial business contents under each financial theme, wherein the financial business contents are defined through the description documents of the financial products; and a third-level product directory, including the product name set for each financial business content and the key business indicators defined for each product name, wherein the product name is defined based on the product type.

[0009] Optionally, the business indicator management method for financial products further includes: receiving field quality monitoring rules selected by the user on the portal page, wherein the field quality monitoring rules are selected from an indicator quality rule library, which includes quality monitoring rules for recommended fields corresponding to each key business indicator; generating a monitoring task based on the monitoring field rules selected by the user on the portal page; executing the monitoring task to obtain monitoring results; generating a field data quality report if the monitoring results indicate an anomaly; and sending the field data quality report to the responsible party and pushing it to the indicator monitoring page.

[0010] Optionally, the business indicator management method for financial products further includes: matching user permission levels based on user identity identifiers indicated by the user terminal; generating database query constraints corresponding to the user permission levels; and, upon receiving a data query request initiated by the user terminal, generating lake table query results based on the database query constraints and returning the lake table query results to the user terminal.

[0011] Optionally, the business indicator management method for financial products further includes: receiving indicator query requests initiated by the financial management terminal or the risk business terminal; responding to the indicator query requests and returning the indicator data of key business indicators of the financial institution's head office and its branches to the display page of the financial management terminal or the risk business terminal.

[0012] According to another aspect of the present invention, a business indicator management system for financial products is also provided, comprising: a product tree and indicator library module for storing a target product tree and key business indicators defined for each financial product; a data lake module for storing raw field data and processed data tables from various business coefficients; and an intelligent mapping engine module for executing the business indicator management method for financial products described in any one of the above embodiments.

[0013] Optionally, the business indicator management system for financial products also includes: a quality and risk monitoring engine module, which generates field quality monitoring rules for key lake table fields based on the mapping relationship between business indicators and recommended fields, and schedules their execution on a regular basis to generate data quality reports; and a data quality report center module, which is used to centrally display the automatically generated data quality reports.

[0014] Optionally, the business indicator management system for financial products further includes: a product indicator management portal module, which provides a unified visual interface for managing the target product tree, defining key business indicators, confirming system-recommended mapping relationships, and managing permissions through the visual page; a dashboard / risk dashboard module, which is directed to the management end and the risk business end, displaying indicator data of key business indicators for the financial institution's head office and its branches; a dynamic permission engine, which matches user permission levels based on the user identity identifier indicated by the user terminal; generates database query constraints corresponding to the user permission levels; and, upon receiving a data query request initiated by the user terminal, generates lake table query results based on the database query constraints and returns the lake table query results to the user terminal.

[0015] Optionally, the field recommendation model is pre-built. Building the field recommendation model includes: constructing a node feature matrix and an adjacency matrix based on the description document, historical mapping relationship, and associated business terms for each business indicator; wherein the node feature matrix includes feature vectors of multiple nodes, and the adjacency matrix includes connection relationships between multiple nodes; the nodes are used to represent business indicators; constructing a graph attention network model based on the node feature matrix and the adjacency matrix; and establishing a mapping relationship between each node and a business term in the graph attention network model to generate the field recommendation model.

[0016] Optionally, the target product tree is pre-built, and the built target product tree includes: a first-level theme directory, including multiple financial themes; a second-level business directory, including multiple financial business contents under each financial theme, wherein the financial business contents are defined through the description documents of the financial products; and a third-level product directory, including the product name set for each financial business content and the key business indicators defined for each product name, wherein the product name is defined based on the product type.

[0017] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the business indicator management method of any of the above-mentioned financial products.

[0018] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the business indicator management method for financial products described above.

[0019] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps of the business indicator management method for the financial product described in any one of the above embodiments.

[0020] In this disclosure, a product addition request is received from a user, and the product name of the new financial product is extracted from the request. A lightweight text classification model is used to analyze the semantics of the product name. Based on the semantic information of the product name and hierarchical constraint rules, a product-level recommendation directory is output, which includes the target hierarchical position of the recommended new financial product in the target product tree. A natural language model is used to extract key business indicators associated with the new financial product in the target product tree. These key business indicators are mapped to a field recommendation model, which queries the field data of the data lake table and outputs recommended fields. The mapping relationship between the key business indicators and the recommended fields is stored in the target knowledge base.

[0021] Based on the aforementioned publicly available information, a lightweight text classification model can be used to analyze the semantics of product names. Combining the semantic information of product names with hierarchical constraint rules, a product hierarchy recommendation directory can be output. Simultaneously, a natural language model extracts key business indicators related to newly added financial products in the target product tree. These key business indicators are then mapped to a field recommendation model, which queries the field data in the data lake table and outputs recommended fields. This achieves intelligent association between key business indicators and data lake fields, supporting seamless integration and in-depth analysis of cross-system data. It can break down data silos and improve the automation rate of product information maintenance, key business indicator definition, and data mapping, significantly reducing labor costs and improving the efficiency of data query and analysis. This solves the technical problem in related technologies where the lack of a correlation mechanism between key business indicators and data tables in the underlying data lake during the management of financial product information easily leads to data silos. Attached Figure Description

[0022] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0023] Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a business indicator management method for financial products is shown.

[0024] Figure 2 This is a flowchart of an optional financial product business indicator management method according to an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of an optional intelligent management system for key business indicators of financial products according to an embodiment of the present invention.

[0026] Figure 4 This is a schematic diagram of an optional intelligent method for key business indicators of financial products according to an embodiment of the present invention;

[0027] Figure 5 This is a structural block diagram of an electronic device that performs a business indicator management method for financial products according to an embodiment of this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] To facilitate understanding of the present invention by those skilled in the art, some terms or nouns involved in the various embodiments of the present invention are explained below:

[0031] A data lake, or DL ​​for short, is a centralized storage system used to store large amounts of raw data and processed data tables. It can accommodate structured, semi-structured, and unstructured data, allowing banks to perform flexible data integration and analysis. In this invention, the data lake serves as the data source for an intelligent mapping engine, automatically mapping and associating it with key business metrics, breaking down data silos, and supporting real-time data access.

[0032] Natural Language Processing (NLP) is used to process and understand human natural language. In this invention, NLP is used to analyze the names and descriptions of business metrics to achieve intelligent matching with data lake fields.

[0033] Machine learning (ML) enables computers to learn from data and improve algorithms without explicit programming. This invention utilizes machine learning techniques to achieve product tree hierarchy recommendations and matching key business metrics with data fields.

[0034] Graph Attention Network (GAT) is a deep learning model used to process graph-structured data. GAT assigns different weights to the information of neighboring nodes by calculating attention coefficients between nodes, thus focusing more on important nodes during the aggregation process and improving the efficiency and accuracy of graph data processing. In this invention, GAT is used in an intelligent mapping engine to optimize the correlation between key business metrics and data lake fields.

[0035] MLP, or Multilayer Perceptron for short, is a type of feedforward neural network consisting of an input layer, an output layer, and one or more hidden layers. In this invention, MLP is used to construct a classification model to predict the product tree level to which a product metric belongs.

[0036] It should be noted that the business indicator management method and system for financial products disclosed herein can be used in the field of fintech to achieve intelligent management of key business indicators of financial products based on fintech, and can also be used in any field other than fintech to achieve intelligent management of key business indicators of financial products based on fintech. This disclosure does not limit the application areas of the business indicator management method and system for financial products.

[0037] It should be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, and displayed data) collected in this public disclosure are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant regions, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse. For example, this system has interfaces with relevant users or organizations. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained only after receiving consent from the aforementioned user or organization.

[0038] It should be noted that in this disclosure, customer information is collected and analyzed, and users are provided with corresponding operation entry points to choose whether to agree to or reject the automated decision results; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0039] The following embodiments of the present invention can be applied to systems / applications / devices for managing business indicators of various financial products. The present invention is applicable to data management and analysis scenarios in the financial field. For example, in product management and optimization scenarios, and in financial product design and lifecycle management, the present invention can provide a real-time view of product performance, including scale, asset quality, and risk status, helping banks optimize product structure and improve customer experience. In risk control and early warning scenarios, for businesses such as credit and wealth management, the present invention can monitor changes in key business indicators in real time, provide dynamic early warnings of data quality and business risks, and assist banks in building a rapid-response risk control system.

[0040] This invention, by introducing automated management and intelligent analysis technologies, can significantly improve the automation rate of product information maintenance, key business indicator definition, and data mapping, greatly reduce labor costs, and improve the efficiency of data query and analysis. It breaks down data silos, enabling intelligent association between key business indicators and data lake fields, and supports seamless integration and in-depth analysis of cross-system data.

[0041] This invention can build a real-time monitoring system for data quality and business risks, shorten the time lag in problem discovery, shift from traditional post-event spot checks to proactive monitoring, and improve the timeliness and accuracy of risk response.

[0042] The present invention will now be described in detail with reference to various embodiments.

[0043] Example 1

[0044] According to an embodiment of the present invention, an embodiment of a business indicator management method for financial products is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0045] The business indicator management method for financial products provided in Embodiment 1 of this application can be executed on mobile terminals, computer terminals, or similar computing systems. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a business indicator management method for financial products is shown. Figure 1 As shown, computer terminal 10 (or mobile device) may include one or more ( Figure 1The processor 102 (which may include, but is not limited to, a microprocessor MCU (Microcontroller Unit) or a programmable gate array (FPGA)) is shown as 102a, 102b, ..., 102n. It also includes a memory 104 for storing data and a transmission system 106 for communication functions. In addition, it may include: a display, an input / output interface (I / O interface), a Universal Serial Bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the electronic system described above. For example, the computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0046] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0047] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage system corresponding to the business indicator management method for financial products in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned business indicator management method for financial products. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0048] The transmission system 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission system 106 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission system 106 may be a radio frequency (RF) module used for wireless communication with the Internet.

[0049] The display can be, for example, a touchscreen liquid crystal display (LCD), which allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0050] Under the aforementioned operating environment, this application provides the following: Figure 2 The business indicator management method for the financial products shown. Figure 2 This is a flowchart of an optional business indicator management method for financial products according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes the following steps S201 to S205. The present invention will be described in detail below with reference to each implementation step.

[0051] Step S201: Receive a product addition request from the user and extract the product name of the new financial product from the product addition request.

[0052] In this embodiment, a front-end portal can be used to target the internal business side of a financial institution. When a new financial product needs to be added, the business side submits a product addition request through the portal. The product addition request includes detailed information about the new financial product, especially the core field of product name.

[0053] Extracting product names involves processing the text data input by the user to ensure the accuracy of the information obtained. Preprocessing steps, such as removing special characters and standardizing text formatting, can improve the recognition rate and parsing accuracy of the product names.

[0054] Step S202: Analyze the semantics of product names using a lightweight text classification model. Based on the semantic information of product names and hierarchical constraint rules, output a product hierarchical recommendation directory. The product hierarchical recommendation directory includes the target hierarchical position of the newly added financial products in the target product tree.

[0055] In this embodiment, a lightweight text classification model can be used to analyze the semantic information of product names. The design goal of the text classification model is to map product names to appropriate category directories. The system generates a product hierarchy recommendation directory through the following steps: Text Feature Extraction: The model encodes the product names and extracts their semantic features. For example, "personal first-hand housing loan" will be encoded into a series of vector features, which can reflect the semantic information of keywords such as "personal," "first-hand housing," and "loan"; Hierarchical Prediction: At the top of the model, two independent multilayer perceptron (MLP, an artificial neural network model) classification layers are added to predict the primary and secondary categories to which new products should belong, respectively. For example, for "personal first-hand housing loan," the primary classification layer may predict that the "loan" category has the highest probability, while the secondary classification layer further predicts the subcategory of "personal loan." Hierarchical rule filtering: Based on the prediction results and the hierarchical constraints of the existing product tree, classification suggestions that do not conform to the logical hierarchy are filtered out. For example, if the model predicts a product belongs to the "financial management" category, but predicts "loan" in the first-level category, the system will perform logical verification to ensure that the recommended classification path conforms to the structural logic of the bank's product tree. Finally, the system will output a recommendation directory, which contains the target hierarchical position of the new product in the target product tree. For example, for "personal new home loan", the system will output a recommendation path such as "credit category → personal loan → new home loan" for the business side to refer to and confirm.

[0056] Step S203: Use a natural language model to extract key business indicators related to newly added financial products in the target product tree.

[0057] This embodiment uses a pre-trained natural language model to perform deep semantic analysis on product names and defined business indicators. The model can understand the meaning of financial product names and the potential correlation between them and the corresponding business indicators. For example, "personal first-hand housing loan" may be highly correlated with indicators such as "loan balance" and "loan default rate".

[0058] Through comparative analysis, the natural language model can recommend a set of key business indicators based on the names of newly added financial products. Optionally, the recommendation process is based on the similarity calculation between the semantic features of the product name and existing indicator names in the indicator library, as well as the association patterns between products and indicators in historical data. It should be noted that although the model can provide intelligent indicator recommendations, the final confirmation and adjustment still need to be made by the business side based on actual business needs and understanding. The portal interface will display a list of indicators recommended by the model, which the business side can select, modify, or add to ensure the accuracy and applicability of the indicators.

[0059] Optionally, the target product tree is pre-built, and the built target product tree includes: a first-level theme directory, including multiple financial themes; a second-level business directory, including multiple financial business contents under each financial theme, and the financial business contents are defined through the description documents of the financial products; and a third-level product directory, including the product name set for each financial business content and the key business indicators defined for each product name, and the product name is defined based on the product type.

[0060] In this embodiment, the target product tree begins with a first-level directory consisting of multiple financial themes, covering the main business areas of financial institutions, such as loans, wealth management, and insurance. The second-level business directories are further refined: under each financial theme, multiple specific financial business contents are defined through product release documentation, forming second-level directories. For example, under the "Loans" theme, the second-level directories might include "Personal Loans," "Corporate Loans," etc. Furthermore, the third-level product directories further refine the financial business contents, including specific product names defined based on product type, and key business indicators defined for each product. For example, under "Personal Loans," there are products such as "Personal New Home Loans" and "Personal Used Home Loans," each associated with specific business indicators.

[0061] Step S204: Map key business metrics to the field recommendation model, and use the field recommendation model to query the field data of the data lake table and output recommended fields.

[0062] Optionally, the step of querying field data from the data lake table using the field recommendation model and outputting recommended fields includes: analyzing the indicator names and description text of key business indicators using the field recommendation model to obtain indicator semantic information; calculating the similarity between the key business indicators and the field names, annotation information, and inter-table relationships of each field in the data lake table based on the indicator semantic information; filtering out multiple fields with similarity greater than a preset similarity threshold to obtain recommended fields; establishing a mapping relationship between key business indicators and recommended fields, and outputting the recommended fields.

[0063] In this embodiment, the field recommendation model first analyzes the indicator names and descriptive text of key business indicators, using natural language processing technology to extract semantic information of the indicators and establish the basis for the association between indicators and fields. Then, based on the extracted semantic information of the indicators, the model calculates the similarity between the key business indicators and the field names, annotation information, and relationships between multiple data tables in the data lake table. The calculation process may involve various matching algorithms, such as cosine similarity and Jaccard similarity, to quantify the degree of semantic association between indicators and fields.

[0064] The system filters out multiple fields with a similarity greater than a preset similarity threshold; these fields are candidate fields with a high correlation to the metrics. Then, a mapping relationship is established between key business metrics and recommended fields, reflecting the direct or indirect connection between business metrics and data fields.

[0065] Optionally, the field recommendation model is pre-built. The construction of the field recommendation model includes: constructing a node feature matrix and an adjacency matrix based on the description document, historical mapping relationships, and associated business terms for each business indicator. The node feature matrix includes feature vectors of multiple nodes, and the adjacency matrix includes connection relationships between multiple nodes. Nodes are used to represent business indicators. A graph attention network model is constructed based on the node feature matrix and the adjacency matrix. For each node in the graph attention network model, a mapping relationship is established between the node and the business terms to generate the field recommendation model.

[0066] When constructing the field recommendation model, historical mapping relationships, indicator description documents, and related business terms were used to build the node feature matrix and adjacency matrix. The node feature matrix contains feature vectors representing the nodes that constitute the business indicators, encoding the semantic information of the indicators. The adjacency matrix represents the connection relationships between nodes, reflecting the association between business indicators and terms / fields.

[0067] Based on the constructed node feature matrix and adjacency matrix, this embodiment employs a Graph Attention Network (GAT) model. GAT can process graph-structured data and focuses on neighboring nodes that have a significant impact on the prediction target by calculating weights. In this scenario, the GAT model utilizes the feature information of nodes and the graph structure to learn the potential correlation between fields and indicators, providing a more intelligent decision-making basis for field recommendations.

[0068] In this embodiment, once the mapping relationship between key business metrics and recommendation fields in the data lake table is established and confirmed by the business side, the next step is to store these mapping relationships in the target knowledge base.

[0069] Step S205: Store the mapping relationship between key business metrics and recommended fields in the target knowledge base.

[0070] Based on the system's recommendations, business stakeholders can confirm or adjust the recommended fields according to their own business understanding to ensure the accuracy and applicability of the mapping relationships and avoid data mismatches caused by semantic differences between data lake fields and business metrics. The confirmed mapping relationships are stored in the target knowledge base, which stores all products, key business metrics and their mapping relationships with data lake table fields, as well as important information such as data quality rules. Updating the knowledge base ensures that the latest metric-field mapping information is preserved, providing a basis for subsequent data access and analysis.

[0071] It should be noted that the target knowledge base in this embodiment may employ graph database technology to store product trees, business metrics, data lake fields, and the relationships between them in the form of a graph. This facilitates efficient querying and analysis in large-scale data environments. Each node (product, metric, field) has its unique attributes and feature vectors, while edges (relationships) carry weight information, representing the strength of the relationship between nodes.

[0072] Through the above steps, we can receive product addition requests from users, extract the product names of the new financial products from these requests, analyze the semantics of the product names using a lightweight text classification model, and output a product-level recommendation directory based on the semantic information of the product names and hierarchical constraint rules. This product-level recommendation directory includes the target hierarchical position of the recommended new financial products in the target product tree. We then use a natural language model to extract key business indicators associated with the new financial products in the target product tree. These key business indicators are mapped to a field recommendation model, which queries the field data in the data lake table and outputs recommended fields. Finally, we store the mapping relationship between the key business indicators and the recommended fields in the target knowledge base. In this embodiment, a lightweight text classification model can be used to analyze the semantics of product names. Combining the semantic information of product names with hierarchical constraint rules, a product hierarchical recommendation directory is output. Simultaneously, a natural language model extracts key business indicators associated with newly added financial products in the target product tree. These key business indicators are mapped to a field recommendation model, which queries the field data of the data lake table and outputs recommended fields. This achieves intelligent association between key business indicators and data lake fields, supports seamless integration and in-depth analysis of cross-system data, breaks down data silos, and improves the automation rate of product information maintenance, key business indicator definition, and data mapping. It significantly reduces labor costs and improves the efficiency of data query and analysis, thereby solving the technical problem in related technologies where the lack of a correlation mechanism between key business indicators and data tables in the underlying data lake during the management of financial product information easily leads to data silos.

[0073] Optionally, the business indicator management method for financial products also includes: receiving field quality monitoring rules selected by the user on the portal page, wherein the field quality monitoring rules are selected from the indicator quality rule library, which includes quality monitoring rules for recommended fields corresponding to each key business indicator; generating monitoring tasks based on the monitoring field rules selected by the user on the portal page; executing the monitoring tasks and obtaining monitoring results; generating a field data quality report when the monitoring results indicate anomalies; and sending the field data quality report to the responsible party and pushing it to the indicator monitoring page.

[0074] In this embodiment, the business indicator management method for financial products, in addition to the aforementioned intelligent mapping and knowledge base updates, also includes field quality monitoring and anomaly reporting functions. Users can select the field quality rules to be monitored on the portal page. These rules originate from an indicator quality rule library, which centralizes quality monitoring rules for recommended fields corresponding to all key business indicators. For example, for the indicator "Personal First-hand Housing Loan Balance," recommended fields may include quality monitoring rules such as "Non-empty check" and "Value range check." Users select suitable rules based on business needs and risk preferences. Once users select monitoring rules on the portal page, the system generates specific monitoring tasks based on the selected rules. The generation process of monitoring tasks is automated, ensuring that the rules are accurately applied to the corresponding data lake table fields. Subsequently, the system executes these monitoring tasks periodically or in real-time to check whether the field data meets the set quality standards. For example, the system can execute "Non-empty check" and "Value range check" tasks once every night to ensure the data integrity and reasonableness of the "Personal First-hand Housing Loan Balance" field.

[0075] During the execution of monitoring tasks, if the monitoring results indicate data anomalies, the system will automatically generate a field data quality report. The report details the specific problems with the anomalous field, such as excessive null values ​​or values ​​exceeding expected ranges, and provides statistical information and the potential impact of the anomalous data. Once the field data quality report is generated, the system will send it to the responsible party (i.e., the designated business personnel or data management personnel) so that timely corrective measures can be taken. Simultaneously, the report will also be pushed to the indicator monitoring page, which can be an integrated interface displaying the latest monitoring status and report information for all key business indicators. Through this page, relevant personnel can quickly understand the overall data health status of the financial product and promptly identify and address potential risks.

[0076] Optionally, the business indicator management method for financial products also includes: matching user permission levels based on user identity identifiers indicated by the user terminal; generating database query constraints corresponding to user permission levels; and, upon receiving a data query request initiated by the user terminal, generating lake table query results based on the database query constraints and returning the lake table query results to the user terminal.

[0077] When a user initiates an operation, the system automatically matches the corresponding user permission level based on the user's identity identifier. This helps ensure that only authorized users can access specific levels of data, thereby maintaining data security and privacy protection. Based on the matched user permission level, the system automatically generates database query constraints. These constraints are embedded in the SQL query statement, limiting the query scope and allowing users to access only data matching their permissions. For example, users of branch A will only receive key business indicator data related to branch A and its subordinate institutions, preventing data leakage and ensuring the compliance of data queries.

[0078] Upon receiving a data query request from a user, the system efficiently generates a lake table query result based on database query constraints. This result is then returned to the user, enabling business personnel to quickly obtain the necessary business metrics data for analysis and decision-making. This instant feedback capability greatly improves work efficiency and helps business personnel make accurate judgments in their daily work.

[0079] Optionally, the business indicator management method for financial products may also include: receiving indicator query requests initiated by the financial management terminal or the risk business terminal; responding to the indicator query requests and returning the indicator data of key business indicators of the financial institution's head office and its branches to the display page of the financial management terminal or the risk business terminal.

[0080] In this embodiment, for indicator queries on the financial management or risk management side, comprehensive monitoring and analysis of key business indicators for the entire financial institution and its various branches and sub-branches is provided. Upon responding to an indicator query request, the system can quickly access information from the data lake module, integrating key business indicator data from the head office and various branches, and then returning it in a clear format to the display page on the financial management or risk management side. This helps management and risk control departments to grasp the bank's overall risk status and business performance in real time, quickly identify potential problem areas, and thus promote precise risk management and decision-making.

[0081] The following is a detailed description with reference to another embodiment.

[0082] Example 2

[0083] The business indicator management system for a financial product provided in this embodiment includes multiple implementation units, each of which corresponds to a specific implementation step in Embodiment 1 above. The specific implementation method and beneficial effects can be referred to the aforementioned method embodiment, and will not be repeated here.

[0084] According to another aspect of the present invention, a business indicator management system for financial products is also provided, comprising: a product tree and indicator library module for storing a target product tree and key business indicators defined for each financial product; a data lake module for storing raw field data and processed data tables from various business coefficients; and an intelligent mapping engine module for executing the business indicator management method for financial products of any one of the above.

[0085] Optionally, the business indicator management system for financial products also includes: a quality and risk monitoring engine module, which generates field quality monitoring rules for key lake table fields based on the mapping relationship between business indicators and recommended fields, and schedules their execution on a regular basis to generate data quality reports; and a data quality report center module, which is used to centrally display the automatically generated data quality reports.

[0086] Optionally, the business indicator management system for financial products also includes: a product indicator management portal module, which provides a unified visual interface for managing the target product tree, defining key business indicators, confirming system-recommended mapping relationships, and managing permissions through a visual page; a dashboard / risk dashboard module, which is for management and risk business ends, displaying indicator data of key business indicators for the financial institution's head office and its branches; a dynamic permission engine, which matches user permission levels based on the user identity identifier indicated by the user terminal; generates database query constraints corresponding to the user permission level; and, upon receiving a data query request initiated by the user terminal, generates lake table query results based on the database query constraints and returns the lake table query results to the user terminal.

[0087] Optionally, the field recommendation model is pre-built. The construction of the field recommendation model includes: constructing a node feature matrix and an adjacency matrix based on the description document, historical mapping relationships, and associated business terms for each business indicator. The node feature matrix includes feature vectors of multiple nodes, and the adjacency matrix includes connection relationships between multiple nodes. Nodes are used to represent business indicators. A graph attention network model is constructed based on the node feature matrix and the adjacency matrix. For each node in the graph attention network model, a mapping relationship is established between the node and the business terms to generate the field recommendation model.

[0088] Optionally, the target product tree is pre-built, and the built target product tree includes: a first-level theme directory, including multiple financial themes; a second-level business directory, including multiple financial business contents under each financial theme, and the financial business contents are defined through the description documents of the financial products; and a third-level product directory, including the product name set for each financial business content and the key business indicators defined for each product name, and the product name is defined based on the product type.

[0089] Figure 3This is a schematic diagram of an optional intelligent management system for key business indicators of financial products according to an embodiment of the present invention, such as... Figure 3 As shown, the system architecture mainly consists of three layers and nine modules: the application layer, the data foundation layer, and the intelligent core layer. The application layer includes: a product indicator management portal module, providing a unified visual interface for business personnel to manage product trees, define key business indicators, confirm system-recommended mapping relationships, and manage permissions; a leadership dashboard / risk dashboard module, designed for management and risk business managers, centrally displaying key indicators for the entire bank and its various institutions, and supporting drill-down to lower-level institutional views or detailed data by clicking on charts; and a data quality report center module, which centrally displays automatically generated data quality reports, highlighting problematic fields and their impact scope, and communicating this information to relevant business units.

[0090] The data foundation layer includes: a product tree and indicator library module, which stores a unified, hierarchical product tree across the entire bank and key business indicators defined for each product, which can be maintained by the business side through an interface; a data lake module, which centrally stores raw data and processed data tables from various business systems; and a metadata and lineage management system module, which records the fields, attributes, sources, and inter-table relationships (lineage) of all data tables, providing a foundation for automatic mapping.

[0091] The intelligent core layer includes: an intelligent mapping engine module, which uses natural language processing models and machine learning techniques to automatically analyze the names and descriptions of business metrics (such as "personal consumer loan balance") and calculate similarity with field names, comments, and lineage relationships in the data lake tables, automatically or semi-automatically establishing a mapping relationship of "product key business metrics <-> lake table fields". For example, the engine can automatically map "personal consumer loan balance" to the loan_balance field in table A. A dynamic permission engine module automatically generates query statements with permission constraints based on user identity, queries the lake tables in the data lake, and returns the results to the user. A quality and risk monitoring engine module automatically generates quality rules (such as NOT NULL and value range checks) for key lake table fields based on the mapping relationship, schedules their execution periodically, and generates data quality reports.

[0092] Figure 4 This is a schematic diagram of an optional intelligent method for key business indicators of financial products according to an embodiment of the present invention, such as... Figure 4As shown, the specific process includes: constructing a bank product tree through a three-level directory structure. First, defining the primary theme directory of products based on the business areas within the bank's subsystems, such as loans and wealth management. Second, defining the secondary business directory based on the product release documentation, such as personal loans, corporate loans, private banking wealth management, and agency wealth management. Third, defining the tertiary product directory based on product type, for example, differentiating personal loans into new home loans, used home loans, and student loans. This three-level product tree, constructed through theme-business definition-product type, forms a unified view interface, allowing business stakeholders to modify and adjust the directory hierarchy and names through the portal.

[0093] For new products, after entering the product name in the portal interface, the system automatically generates a product hierarchy recommendation directory. For example, after entering the product name "Personal Consumer Loan" in the portal interface, the system automatically recommends the directory hierarchy "Loans - Personal Loans". The specific new product directory hierarchy recommendation can employ a combination of a lightweight text classification model and hierarchical constraint rules. In this embodiment, the product tree is a complete and accurate label classification dataset. A Chinese pre-trained model is used as the text encoder, possessing excellent semantic understanding capabilities. For example, after analyzing "New Energy Vehicle Loan", the output vector 1 [0.82, -0.15, 0.37, ...] represents new energy, vector 2 [0.75, 0.02, -0.41, ...] represents automobiles, and vector 3 [0.79, 0.01, -0.34, ...] represents loans. The final output is a comprehensive semantic vector representing the overall meaning [0.78, -0.08, 0.21, ...]. Two independent multilayer perceptron classification layers are added on top of the Chinese pre-trained model to predict primary and secondary classifications respectively. For example, the first-level classification layer outputs: Loans (80% probability), Investments (15% probability), and Insurance (5% probability). The second-level classification layer outputs: Personal Loans (70% probability) and Business Loans (25% probability). Finally, branches that do not conform to the hierarchical rules are filtered from the model's predicted first-level classification results. Under the filtered candidate first-level classifications, the path with the highest probability of the second-level classification is selected. For example, if insurance products are not under the loan category, the final model output will be "Loans - Personal Loans".

[0094] Based on the defined product tree, key business indicators are defined for each end-product. For example, for personal consumer loans, indicator names such as "Personal Consumer Loan Balance" and "Personal Consumer Loan Non-Performing Amount" can be added. The intelligent mapping module mainly maps key business indicators to lake tables and their fields in a recommendation model. High-accuracy automated recommendations are achieved by employing "semantic similarity matching + graph attention network". Specifically, natural language models are used to extract semantic features of indicator names, and candidate fields are generated through joint embedding based on statistical methods for evaluating the importance of words in documents and models that convert words into vectors. For example, for the "Personal First-hand Housing Non-Performing Loan Balance", candidate fields generated would be: "Non-Performing Loan Amount" and "Non-Performing Loan Balance".

[0095] Simultaneously, historical mapping relationships, field lineage, and business terminology are stored in the graph database, and the initial characteristics of the nodes are defined:

[0096] Business Indicator 1: Feature Vector = V_indicator1 (derived from "Non-Performing Individual First-Hand Housing Loans" and its descriptive encoding);

[0097] Business term A: Feature vector = V_termA (derived from "personal loan" encoding);

[0098] Business term B: Feature vector = V_termB (derived from "bad" encoding);

[0099] Table 1: Feature vector = V_table1 (encoded from table name and table comments);

[0100] Field B: Feature vector = V_fieldB (derived from the field name loan_by_amt and its annotation encoding);

[0101] Field C: Feature vector = V_fieldC (encoded from an unrelated field);

[0102] Define the edge features of the graph:

[0103] Business Indicator 1 -- Related -- Business Terminology A;

[0104] Business Indicator 1 -- Related -- Business Terminology B;

[0105] Business term A -- mapped to --> field B (historical mapping relationship);

[0106] Business term A -- Belongs to --> surface;

[0107] Business term B -- mapped to --> field B (historical mapping relationship);

[0108] Field B -- Belongs to --> surface.

[0109] Construct a GAT (Graph Attention Network) model, representing the graph as G=(X,A). X is the node feature matrix, where each row is a feature vector of a node; A is the adjacency matrix, representing the connections between nodes. In heterogeneous graphs (with multiple edge types), for simplicity, relationship types can be ignored initially, or different GAT layers can be used for different types of relationships. When a new business metric (such as "personal auto loan default rate") is input, a score is output for this metric and candidate fields. The field with the highest recommendation score is recommended to business personnel. Business personnel confirm or adjust the recommendation results, ultimately forming a reliable "metric-field" mapping pair, which is then stored in the knowledge base.

[0110] When a user selects the desired product metrics and organizational level on the portal interface, the system receives the request and automatically injects permission conditions based on the user's organizational affiliation during data querying. For example, when a user from Branch B queries "Personal Loan Non-Performing Amount," the engine can automatically add `WHERE branch_id LIKE 'SH%'` to the SQL query, ensuring that the user can only see data from branches under Branch B; thus, the user from Branch B can only see data with `WHERE branch_id = 'Pudong'`.

[0111] Based on the established product-metric-field model, the data quality of the fields is monitored, and a rule library for metric quality is built. For example, rules are established for field values ​​that are empty or exceed the threshold. Users can directly select rules in the portal to automatically generate monitoring tasks. When abnormal fluctuations occur, a data quality report is automatically generated and sent to the relevant person in charge. At the same time, specific early warning information can be viewed in a visual manner on the risk dashboard.

[0112] The above embodiments significantly improve the automation rate of new product maintenance and indicator mapping, reducing manual maintenance costs. Simultaneously, data query efficiency is greatly improved, allowing business personnel to obtain data independently; data integration and governance capabilities are enhanced, as the intelligent mapping engine automatically associates business indicators with data lake table fields using natural language processing and machine learning technologies, effectively breaking down data silos; and a quality and risk monitoring engine is built to achieve real-time monitoring of data quality, reducing problem detection time from "days / hours" to "minutes," accurately pinpointing the source of problems.

[0113] Meanwhile, this embodiment can support real-time monitoring of the entire bank's risk status through the cockpit and quickly drill down to locate the root cause of problems, promoting accurate decision-making; in addition, the permission management is more refined and flexible, and the dynamic permission engine automatically generates query database statements with permission constraints based on user identity, meeting the multi-level data access needs of "headquarters-branch-sub-branch", and improving flexibility while ensuring security.

[0114] Example 3

[0115] Embodiments of this application may provide an electronic device. Figure 5 This is a structural block diagram of an electronic device for implementing a business indicator management method for financial products according to an embodiment of this application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 (Only one is shown) processor 502, memory 504, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0116] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the financial product business indicator management method and system in this application embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned financial product business indicator management method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0117] The processor can transfer system calls to the information and application programs stored in the memory to perform the following steps: receiving a product addition request from the user and extracting the product name of the new financial product from the request; analyzing the semantics of the product name using a lightweight text classification model, and outputting a product-level recommendation directory based on the semantic information of the product name and hierarchical constraint rules, wherein the product-level recommendation directory includes the target hierarchical position of the recommended new financial product in the target product tree; extracting key business indicators related to the new financial product in the target product tree using a natural language model; mapping the key business indicators to a field recommendation model, querying the field data of the data lake table using the field recommendation model, and outputting recommended fields; and storing the mapping relationship between the key business indicators and the recommended fields in the target knowledge base.

[0118] Those skilled in the art will understand that Figure 5 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 5 This does not limit the structure of the aforementioned electronic systems. For example, electronic devices may also include components that are more... Figure 5 The more or fewer components shown (such as network interfaces, display systems, etc.), or having the same Figure 5 The different configurations shown.

[0119] Those skilled in the art will understand that all or part of the steps in the business indicator management methods for various financial products in the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0120] Example 4

[0121] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the business indicator management method for the financial product provided in Embodiment 1.

[0122] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the business indicator management method of any one of the above embodiments of the financial product.

[0123] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0124] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the business indicator management method for the financial product described in various embodiments of this application.

[0125] This application also provides a computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the business indicator management method for the financial product described in various embodiments of this application.

[0126] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0127] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0128] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection of units or modules may be electrical or other forms.

[0129] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0130] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0131] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0132] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for managing business indicators of a financial product, characterized in that, include: Receive a product addition request from the user and extract the product name of the new financial product from the product addition request; The semantics of the product name are analyzed using a lightweight text classification model. Based on the semantic information of the product name and hierarchical constraint rules, a product hierarchical recommendation directory is output. The product hierarchical recommendation directory includes the target hierarchical position of the newly added financial product in the target product tree. The key business indicators associated with the newly added financial products in the target product tree are extracted using a natural language model. The key business metrics are mapped to the field recommendation model, which then queries the field data of the data lake table and outputs recommended fields. The mapping relationship between the key business metrics and the recommendation fields is stored in the target knowledge base.

2. The business indicator management method according to claim 1, characterized in that, The steps of querying field data from the data lake table using the field recommendation model and outputting recommended fields include: The semantic information of the key business indicators is obtained by analyzing the indicator names and indicator description texts of the field recommendation model. Based on the semantic information of the indicators, the similarity between the key business indicators and the field names, annotation information, and inter-table relationships of each field in the data lake table is calculated. Multiple fields with a similarity greater than a preset similarity threshold are selected to obtain the recommended fields; Establish a mapping relationship between the key business metrics and the recommended fields, and output the recommended fields.

3. The business indicator management method according to claim 2, characterized in that, The field recommendation model is pre-built, and the construction of the field recommendation model includes: Based on the description document, historical mapping relationship and related business terms of each business indicator, a node feature matrix and an adjacency matrix are constructed. The node feature matrix includes feature vectors of multiple nodes, and the adjacency matrix includes the connection relationship between multiple nodes. The nodes are used to represent business indicators. A graph attention network model is constructed based on the node feature matrix and the adjacency matrix; For each node in the graph attention network model, a mapping relationship between the node and business terms is established to generate the field recommendation model.

4. The business indicator management method according to claim 1, characterized in that, The target product tree is pre-built, and the built target product tree includes: The first-level subject directory includes multiple financial topics; The secondary business directory includes multiple financial business contents under each financial theme, and the financial business contents are defined through the explanatory documents of the financial products. The three-level product catalog includes the product name set for each of the aforementioned financial business items and the key business indicators defined for each product name, with the product name based on the product type definition.

5. The business indicator management method according to claim 1, characterized in that, Also includes: The system receives field quality monitoring rules selected by the user on the portal page. These field quality monitoring rules are selected from an indicator quality rule library, which includes quality monitoring rules for recommended fields corresponding to each key business indicator. Based on the monitoring field rules selected by the user on the portal page, a monitoring task is generated; The monitoring task is executed to obtain monitoring results; If the monitoring results indicate an anomaly, a field data quality report will be generated; The data quality report for the aforementioned fields will be sent to the responsible party and pushed to the indicator monitoring page.

6. The business indicator management method according to claim 1, characterized in that, Also includes: Match the user's permission level based on the user identity identifier indicated by the user client; Generate database query constraints corresponding to the user's permission level; Upon receiving a data query request initiated by the user, a lake table query result is generated based on the database query constraints, and the lake table query result is returned to the user.

7. The business indicator management method according to claim 1, characterized in that, Also includes: Receive indicator query requests initiated by the financial management or risk business departments; In response to the indicator query request, the key business indicator data of the financial institution's head office and its branches are returned to the display page of the financial management terminal or risk business terminal.

8. A business indicator management system for a financial product, characterized in that, include: The product tree and indicator library module is used to store the target product tree and the key business indicators defined for each financial product. The data lake module is used to store the raw field data and processed data tables from various business coefficients; The intelligent mapping engine module is used to execute the business indicator management method for the financial product as described in any one of claims 1 to 4.

9. The business indicator management system according to claim 8, characterized in that, Also includes: The quality and risk monitoring engine module generates field quality monitoring rules for key lake table fields based on the mapping relationship between business metrics and recommended fields, and schedules their execution on a regular basis to generate data quality reports. The Data Quality Report Center module is used to centrally display the automatically generated data quality reports.

10. The business indicator management system according to claim 8, characterized in that, Also includes: The product metrics management portal module provides a unified visual interface for managing the target product tree, defining key business metrics, confirming system-recommended mapping relationships, and managing permissions. The cockpit / risk dashboard module is designed for both management and risk management, displaying key business metrics data for the financial institution's head office and branches. The dynamic permission engine matches user permission levels based on the user identity identifier indicated by the user client. Generate database query constraints corresponding to the user's permission level; Upon receiving a data query request initiated by the user, a lake table query result is generated based on the database query constraints, and the lake table query result is returned to the user.

11. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the business indicator management method for the financial product according to any one of claims 1 to 7.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the business indicator management method for financial products according to any one of claims 1 to 7.

Images