Processing method and device for financial service problem, medium and program product

Abstract

The application discloses a processing method and device for a financial service problem, a medium and a program product. It relates to the field of financial technology, and the method comprises the following steps: receiving a financial service problem of a target object, wherein the financial service problem comprises a pension service-related problem; performing standardized processing on the financial service problem to obtain a standard service problem; obtaining data access authority of the target object, wherein the data access authority comprises access authority for service data of the pension service; determining target reply data by using a target knowledge graph based on the standard service problem and the data access authority, and visually displaying the target reply data, wherein the target knowledge graph comprises a knowledge graph constructed based on pension service-related data in M data sources. Through the application, the problem of low efficiency in replying to pension problems caused by the dispersion of pension service knowledge in related technologies is solved.

Description

Technical Field

[0001] This application relates to the field of financial technology, and more specifically, to a method, apparatus, medium, and program product for processing financial business problems. Background Technology

[0002] Currently, knowledge related to pension business is scattered across multiple data sources, such as multiple operation manuals and multiple financial systems. When faced with inquiries about pension business, it is necessary to search for relevant knowledge from multiple data sources one by one to generate a corresponding answer. Due to the large number of data sources, the efficiency of finding and locating relevant knowledge for inquiries is low, which leads to the inefficiency of answering inquiries.

[0003] There is currently no effective solution to the problem of fragmented knowledge about pension business in related technologies, which leads to low efficiency in responding to pension-related questions. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, medium, and program product for processing financial business issues, in order to solve the problem of low efficiency in responding to pension business issues due to the fragmentation of pension business knowledge in related technologies.

[0005] To achieve the above objectives, according to one aspect of this application, a method for processing financial business questions is provided. The method includes: receiving a financial business question from a target object, wherein the financial business question includes a question related to pension business; standardizing the financial business question to obtain a standard business question; acquiring data access permissions for the target object, wherein the data access permissions include access permissions to business data related to the pension business; determining target response data based on the standard business question and the data access permissions using a target knowledge graph, and visualizing the target response data, wherein the target knowledge graph includes a knowledge graph constructed based on data related to the pension business from M data sources, where M is a positive integer.

[0006] Further, the M data sources include: a financial system and target files. The data in the target files includes at least one of the following: regulatory requirements and business rules for the pension business. The target knowledge graph is obtained through the following methods: extracting structured data from the database of the financial system to obtain first business data; extracting unstructured data from the target files to obtain second business data; extracting entities from the first and second business data to obtain S entities, wherein the categories of the S entities include at least one of the following: product entities, operation entities, and rule entities, where S is a positive integer; identifying the relationships between the S entities and determining the data source for each relationship to obtain a target relationship set; and constructing the target knowledge graph based on the S entities and the target relationship set.

[0007] Furthermore, based on the S entities and the target relation set, the target knowledge graph is constructed, including: constructing nodes representing each entity to obtain S nodes; and establishing connection edges between the S nodes based on the associations in the target relation set and the data source of each association to obtain the target knowledge graph.

[0008] Furthermore, the target response data is visualized, including: identifying the sensitivity level of the financial business question to obtain the target sensitivity level; obtaining visualization rules, wherein the visualization rules include at least one of the following: chart type rules, style specifications; and visualizing the target response data based on the target sensitivity level and the visualization rules.

[0009] Further, identifying the sensitivity level of the financial business issue to obtain a target sensitivity level includes: obtaining all sensitive words associated with each of the S sensitivity levels to obtain S sensitive word sets; identifying whether the financial business issue contains any of the sensitive words in each of the sensitive word sets to obtain an identification result; and determining the sensitivity level associated with the sensitive word set as the target sensitivity level if the financial business issue contains any of the sensitive words in the sensitive word set.

[0010] Furthermore, based on the target sensitivity level and the visualization rules, the target response data is visualized, including: when the target sensitivity level is the first sensitivity level, the target response data is de-identified to obtain de-identified target response data, and the de-identified target response data is visualized based on the visualization rules; when the target sensitivity level is the second sensitivity level, a watermark is added to the target response data to obtain watermarked target response data, and the watermarked target response data is visualized based on the visualization rules; when the target sensitivity level is the third sensitivity level, the target response data is visualized based on the visualization rules.

[0011] Furthermore, the data access permissions include at least one of the following: data access scope, data operation permissions. Based on the standard business question and the data access permissions, the target response data is determined using a target knowledge graph, including: extracting data from the target knowledge graph based on the standard business question to obtain first response data; filtering the first response data based on the data access scope to obtain second response data; setting operation permissions for the second response data based on the data operation permissions, and determining the second response data with set operation permissions as the target response data.

[0012] To achieve the above objectives, according to another aspect of this application, a processing apparatus for financial business questions is provided. The apparatus includes: a receiving unit for receiving a financial business question from a target object, wherein the financial business question includes a question related to pension business; a first processing unit for standardizing the financial business question to obtain a standard business question; an acquiring unit for acquiring data access permissions for the target object, wherein the data access permissions include access permissions to business data related to the pension business; and a second processing unit for determining target response data based on the standard business question and the data access permissions using a target knowledge graph, and visualizing the target response data, wherein the target knowledge graph includes a knowledge graph constructed based on data related to the pension business from M data sources, where M is a positive integer.

[0013] Further, the M data sources include: a financial system and target files. The data in the target files includes at least one of the following: regulatory requirements and business rules for the pension business. The target knowledge graph is obtained through the following sub-units: a first extraction sub-unit, used to extract structured data from the database of the financial system to obtain first business data; a second extraction sub-unit, used to extract unstructured data from the target files to obtain second business data; a third extraction sub-unit, used to extract entities from the first business data and the second business data to obtain S entities, wherein the categories of the S entities include at least one of the following: product entities, operation entities, and rule entities, where S is a positive integer; a determination sub-unit, used to identify the relationships between the S entities and determine the data source of each relationship to obtain a target relationship set; and a construction sub-unit, used to construct the target knowledge graph based on the S entities and the target relationship set.

[0014] Further, the determined sub-unit includes: a construction module, used to construct nodes representing each of the entities, resulting in S nodes; and an establishment module, used to establish connection edges between the S nodes based on the associations in the target relation set and the data source of each association, to obtain the target knowledge graph.

[0015] Furthermore, the second processing unit includes: an identification subunit for identifying the sensitivity level of the financial business issue and obtaining a target sensitivity level; an acquisition subunit for acquiring visualization rules, wherein the visualization rules include at least one of the following: chart type rules and style specifications; and a display subunit for visually displaying the target response data based on the target sensitivity level and the visualization rules.

[0016] Further, the identification subunit includes: an acquisition module, used to acquire all sensitive words associated with each of the S sensitivity levels to obtain S sensitive word sets; an identification module, used to identify whether the financial business problem contains any of the sensitive words in each of the sensitive word sets to obtain an identification result; and a determination module, used to determine the sensitivity level associated with the sensitive word set as the target sensitivity level if the financial business problem contains any of the sensitive words in the sensitive word set.

[0017] Furthermore, the display subunit includes: a first processing module, configured to, when the target sensitivity level is a first sensitivity level, perform desensitization processing on the target response data to obtain desensitized target response data, and visualize the desensitized target response data based on the visualization rules; a second processing module, configured to, when the target sensitivity level is a second sensitivity level, add a watermark to the target response data to obtain watermarked target response data, and visualize the watermarked target response data based on the visualization rules; and a display module, configured to, when the target sensitivity level is a third sensitivity level, visualize the target response data based on the visualization rules.

[0018] Furthermore, the data access permissions include at least one of the following: data access scope, data operation permissions, and the second processing unit includes: an extraction subunit, used to extract data from the target knowledge graph based on the standard business question to obtain first response data; a filtering subunit, used to filter the first response data based on the data access scope to obtain second response data; and a processing subunit, used to set the operation permissions of the second response data based on the data operation permissions, and to determine the second response data with the set operation permissions as the target response data.

[0019] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored executable program, wherein, when the executable program is executed, it controls the device where the computer-readable storage medium is located to perform the processing method for financial business problems.

[0020] According to another aspect of this application, an electronic device is provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program, when running, performs the processing method for financial business problems.

[0021] According to another aspect of this application, a computer program product is provided, including computer instructions that, when executed by a processor, implement the steps of the processing method for financial business problems.

[0022] This application employs the following method: receiving financial business questions from the target object, whereby the financial business questions include questions related to pension business; standardizing the financial business questions to obtain standard business questions; obtaining data access permissions from the target object, whereby the data access permissions include access permissions to business data related to pension business; based on the standard business questions and data access permissions, using a target knowledge graph to determine target response data, and visually displaying the target response data, whereby the target knowledge graph includes a knowledge graph constructed based on pension business-related data from M data sources, thereby solving the technical problem of low efficiency in responding to pension questions due to the dispersion of pension business knowledge in related technologies. In this application, by integrating a knowledge graph of pension business data from multiple data sources to respond to pension business inquiries, the dispersion of pension business knowledge leading to low efficiency in locating the response knowledge for pension questions is avoided, thus achieving the technical effect of improving the efficiency of responding to pension business inquiries. Attached Figure Description

[0023] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0024] Figure 1 A hardware block diagram of a computer terminal for implementing a method for processing financial business problems is shown.

[0025] Figure 2 This is a flowchart of a method for handling financial business issues provided according to an embodiment of this application;

[0026] Figure 3 This is a schematic diagram of the target knowledge graph provided according to an embodiment of this application;

[0027] Figure 4 This is a flowchart of sensitive data processing for financial business consultation issues provided in the embodiments of this application;

[0028] Figure 5 This is a flowchart of a financial business problem provided according to an embodiment of this application;

[0029] Figure 6 This is a flowchart of a financial business problem provided according to an embodiment of this application;

[0030] Figure 7 This is a schematic diagram of a processing apparatus for financial business issues provided according to an embodiment of this application;

[0031] Figure 8 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0033] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application 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 this application 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 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.

[0034] It should be noted that the method and apparatus for processing financial business issues in this application can be used in the field of fintech to answer inquiries about pension business, and can also be used in any field other than fintech to answer inquiries about pension business. This application does not limit the application field of the method and apparatus for processing financial business issues.

[0035] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) 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 this data all comply with relevant laws and standards, necessary 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, interfaces are set up between this system and relevant users or organizations, providing users with corresponding operation entry points for them to choose to agree to or refuse automated decision results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0036] This invention can be applied to various software products, control systems, and client applications (including but not limited to mobile clients and PCs) of financial institutions to generate response data when inquiring about pension business.

[0037] Example 1

[0038] According to an embodiment of this application, a method embodiment for processing financial business problems is also 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. 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.

[0039] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a method for processing financial business problems is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also 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 aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0040] 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).

[0041] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the processing method for financial business problems in this embodiment of the application. 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 above-mentioned processing method for financial business problems. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, 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.

[0042] The transmission device 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 device 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 device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0043] 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).

[0044] Under the aforementioned operating environment, this application provides the following: Figure 2 The methods shown are for handling financial business issues. Figure 2 This is a flowchart of a method for handling financial business problems according to Embodiment 1 of this application.

[0045] Step S201: Receive financial business questions from the target object, including questions related to pension business.

[0046] The aforementioned target groups can be financial institutions that provide services to clients, and the aforementioned financial business issues can include: consulting issues related to pension business.

[0047] Step S202: Standardize the financial business problem to obtain the standard business problem.

[0048] In this embodiment, natural language understanding technology can be used to transform unstructured, colloquial, or ambiguous financial business questions into standardized business questions that conform to preset specifications and have clear semantics. For example, lexical analysis can be used to identify core entities in financial business questions, eliminating synonym ambiguity. Furthermore, a preset business terminology database can be used to convert identified entities into synonyms from the database and complete any missing context. Finally, a structured statement (i.e., the standard business question) is output to ensure that the standard business question can accurately match knowledge graph nodes.

[0049] Step S203: Obtain data access permissions for the target object, wherein the data access permissions include: access permissions for business data of pension business.

[0050] In this embodiment, different objects may have different data access permissions (e.g., data access scope, data operation permissions). For example, the head office administrator of a financial institution can access all pension business data and support data download. Branches of a financial institution can only access the pension business data managed by their own branch and can only use it for Q&A. Partner institutions of a financial institution can only access the de-identified pension business data and have read-only operation permissions. This achieves the technical effect of improving the data security of pension business data.

[0051] Step S204: Based on standard business questions and data access permissions, target response data is determined using the target knowledge graph, and the target response data is visualized. The target knowledge graph includes a knowledge graph constructed based on data related to pension business from M data sources, where M is a positive integer.

[0052] The aforementioned target knowledge graph may include: a knowledge graph constructed from data related to pension business from multiple data sources. These multiple data sources may include: financial systems, regulatory requirements for pension business, and rule files (i.e., target files) containing business rules. In this embodiment, the labeled business questions and the target knowledge graph can be matched and searched to obtain initial response data. The initial response data is then processed according to data access permissions to obtain target response data. Finally, the target response data is visualized to answer the financial business questions of the target object.

[0053] Through the steps described above, this embodiment integrates a knowledge graph of pension business data from multiple data sources to answer inquiries about pension business. This avoids the problem of fragmented pension business knowledge leading to low efficiency in locating the correct answer to pension questions, thereby improving the technical efficiency of answering pension inquiries. Furthermore, it solves the technical problem in related technologies where fragmented pension business knowledge leads to low efficiency in answering pension questions.

[0054] Optionally, in the processing method for financial business problems provided in the embodiments of this application, the M data sources include: a financial system and a target file. The data in the target file includes at least one of the following: regulatory requirements and business rules for pension business. The target knowledge graph is obtained by: extracting structured data from the database of the financial system to obtain first business data; extracting unstructured data from the target file to obtain second business data; extracting entities from the first and second business data to obtain S entities, wherein the categories of the S entities include at least one of the following: product entities, operation entities, and rule entities, where S is a positive integer; identifying the relationships between the S entities and determining the data source of each relationship to obtain a target relationship set; and constructing a target knowledge graph based on the S entities and the target relationship set.

[0055] In this embodiment, M data sources can be accessed to obtain pension business data from the M data sources. The M data sources may include financial systems containing structured data and unstructured target files (e.g., relevant implementation measures for pension business, financial product manuals, and other regulatory documents). The target files may contain regulatory requirements and business rules for pension business.

[0056] In this embodiment, differentiated data extraction can be performed on the database of the financial system and unstructured target files to obtain first business data and second business data. For example, structured data (first business data) such as product codes and product descriptions for pension business can be extracted from the database of the financial system. Unstructured data (second business data) can be extracted from the target files through parsing, clause recognition, regular expression matching, etc., to obtain second business data. For example, semantic units such as "Article X, Clause Y" in the target file can be identified.

[0057] Afterwards, entity recognition can be performed on the first business data and the second business data to extract S semantic entities. For example, product entities, operation entities, and rule entities can be extracted. Among them, product entities are such as "Product A" (product code XX); operation entities are such as "account transfer" (operation code XX); and rule entities are such as "Article 3, Paragraph 2 of the Implementation Measures of B".

[0058] In this embodiment, semantic relationships between entities can also be identified from the first business data and the second business data, and the data source of each relationship can be marked (e.g., "Source: Product Manual 8.3"), forming a structured and traceable set of target relationships.

[0059] Finally, a target knowledge graph with entity semantics and relation origins can be constructed using S entities as nodes and the target relation set as directed edges with attributes.

[0060] Figure 3 This is a schematic diagram of the target knowledge graph provided according to the embodiments of this application, such as... Figure 3 As shown, this includes nodes for: early redemption rules, staking rules, and rule documents (corresponding to target documents), relationship edges between holding periods of <1 year and holding periods of ≥1 year, and relationship edges between staking rate and materials.

[0061] In this embodiment, the target knowledge graph can not only achieve deep integration of regulatory documents, financial system data, and business rules, but also be used for intelligent question answering, access control, and compliance verification, avoiding the inefficient situation of manually searching for pension business knowledge from multiple data sources.

[0062] In one alternative example, a component that automatically establishes cross-financial system data associations can also be established through intelligent field matching technology. This can perform fuzzy matching (e.g., "ID number representing customer identity" ≈ "ID number of wealth management system") and automatically inject business cycle conditions (e.g., the "21st of last month - 20th of this month" statistical cycle unique to pension funds).

[0063] In another alternative example, the target knowledge graph described above can be updated periodically, or, in the event of new target files or new pension business data generated in the financial system, the target knowledge graph can be updated based on the new data.

[0064] Optionally, in the processing method for financial business problems provided in the embodiments of this application, a target knowledge graph is constructed based on S entities and a target relation set, including: constructing nodes representing each entity to obtain S nodes; and establishing connection edges between the S nodes based on the associations in the target relation set and the data sources of each association to obtain the target knowledge graph.

[0065] In this embodiment, S extracted entities can be mapped to nodes in a knowledge graph. Each node carries a type label (product class / operation class / rule class) and basic attributes (such as entity name, code, etc.), forming the semantic basic unit of the graph. Secondly, based on each association in the target relation set, directed connections can be established between corresponding nodes, and a "data source" attribute (such as "Source: Product Manual 8.3") can be added to each edge to clarify the source of the semantic relationship. In this way, structured and unstructured data originally scattered across multiple data sources are transformed into a structured, reasonable target knowledge graph. This target knowledge graph not only enables precise linkage between "products, rules, and documents" in pension business but also, based on intelligent question answering and dynamic graph updates, facilitates automated and intelligent pension business problem-solving processes.

[0066] Optionally, in the processing method for financial business issues provided in the embodiments of this application, the target response data is visualized, including: identifying the sensitivity level of the financial business issue and obtaining the target sensitivity level; obtaining visualization rules, wherein the visualization rules include at least one of the following: chart type rules and style specifications; and visualizing the target response data based on the target sensitivity level and the visualization rules.

[0067] In this embodiment, the target sensitivity level of financial business issues can be identified to determine the boundaries of the displayed response data. Subsequently, preset visualization rules can be invoked to visualize the target response data.

[0068] The visualization rules mentioned above may include: chart type rules and style specifications (e.g., font color, chart color, etc.).

[0069] In one optional example, visualization rules may include:

[0070] Rule 1: Triggering conditions: Field name contains "growth rate"; Chart type: Dual-axis line chart; Style specifications: Primary color value: #003366 (row marker blue), Secondary color value: #FF6600 (row marker orange).

[0071] Rule 2: Triggering conditions: Data dimension is "product distribution"; Chart type: pie chart.

[0072] In this embodiment, the target response data is visualized according to the sensitivity level of the financial business issues and visualization rules. This not only ensures that the security risks in handling pension business consultation issues are controllable, but also improves the efficiency of data acquisition, thereby enhancing the processing efficiency and data security of pension business consultation issues.

[0073] Optionally, in the processing method for financial business issues provided in the embodiments of this application, identifying the sensitivity level of the financial business issue and obtaining the target sensitivity level includes: obtaining all sensitive words associated with each of the S sensitivity levels to obtain S sensitive word sets; identifying whether the financial business issue contains any sensitive word in each sensitive word set to obtain an identification result; and determining the sensitivity level associated with the sensitive word set as the target sensitivity level if the financial business issue contains any sensitive word in the sensitive word set.

[0074] In this embodiment, to identify the sensitivity level of financial business questions, a matching mechanism based on sensitive word sets can be used to determine the sensitivity level of the financial business questions. For example, S sensitivity levels can be pre-constructed, with each level associated with a sensitive word set. When a financial business question is raised, the text of the financial business question can be segmented and semantically matched, and each word can be checked to see if it contains keywords from any of the sensitive word sets. If a sensitive word from a certain sensitive word set appears in the financial business question, then the sensitivity level associated with that sensitive word set is determined to be the target sensitivity level. Determining the sensitivity level of financial business questions through sensitive word sets can improve the stability and reliability of sensitive question identification, and provide a basis for subsequent access control and visualization of response data.

[0075] In an alternative example, if the financial business question does not contain any sensitive words from the sensitive word set, it can be determined that the financial business question is not sensitive (i.e., the third sensitivity level).

[0076] Optionally, in the processing method for financial business issues provided in this application embodiment, the target response data is visualized based on the target sensitivity level and visualization rules, including: when the target sensitivity level is the first sensitivity level, the target response data is de-identified to obtain de-identified target response data, and the de-identified target response data is visualized based on visualization rules; when the target sensitivity level is the second sensitivity level, a watermark is added to the target response data to obtain watermarked target response data, and the watermarked target response data is visualized based on visualization rules; when the target sensitivity level is the third sensitivity level, the target response data is visualized based on visualization rules.

[0077] For example, when the target sensitivity level is the highest level (e.g., involving high security risks or a large amount of privacy information), sensitive fields (such as customer ID number, specific amount, and organization code) in the target response data can be automatically anonymized to ensure no privacy is leaked. Then, the anonymized target response data can be displayed according to visualization rules (e.g., color, chart type).

[0078] When the target sensitivity level is the second sensitivity level (e.g., medium-risk content), data content desensitization is not required, but an operation watermark can be added to the target response data, and the source of the basis can be marked (e.g., "Based on: Article 8.3 of the product manual") to achieve data traceability; then, the data can be visualized according to the visualization rules, taking into account both professionalism and readability.

[0079] When the target sensitivity level is the third sensitivity level (such as low-risk content such as process guidance and operation steps), there is no need to desensitize or add watermarks. The graphic and text responses can be generated directly according to the visualization rules and displayed to improve the user experience.

[0080] For example, Figure 4 This is a flowchart of sensitive data processing for financial business consultation issues provided in the embodiments of this application, such as... Figure 4 As shown, after entering a question, the system can perform sensitive word detection. If the question contains a Level 1 sensitive word, it can be identified as Level 1 sensitive and can be de-identified. If the question contains a Level 2 sensitive word, it can be identified as Level 2 sensitive and a watermark can be added. If the question does not contain any sensitive words, it can be handled normally without any processing.

[0081] By employing a multi-level sensitivity mechanism, the system achieves processing that includes "high-sensitivity de-identification to prevent leakage, medium-sensitivity watermarking, and low-sensitivity efficient information display." This not only meets the requirements for data security and accountability but also enables accurate display of responses to financial business questions, thereby improving the reliability and security of responses to financial business questions.

[0082] Optionally, in the processing method for financial business issues provided in the embodiments of this application, the data access permission includes at least one of the following: data access scope, data operation permission. Based on the standard business issue and the data access permission, the target response data is determined using a target knowledge graph, including: extracting data from the target knowledge graph based on the standard business issue to obtain first response data; filtering the first response data based on the data access scope to obtain second response data; setting the operation permission of the second response data based on the data operation permission, and determining the second response data with the set operation permission as the target response data.

[0083] For example, after obtaining a standard financial business question, the target knowledge graph can be queried based on the standard business question to extract the first response data that semantically matches the question. This first response data can include the response content and the data source of the response content. Subsequently, based on the data access scope of the target object (e.g., data limited to a specific branch), the first response data can be filtered by region or institution to remove cross-institutional data, resulting in second response data containing only data within the target object's access scope. For example, business service personnel in region A cannot see customer cases in region B. Then, based on data operation permissions (e.g., "viewable only, not exportable" or "reports can be generated but not downloaded"), access control policies can be set for the second response data, such as adding a read-only watermark, disabling the download button, and restricting printing. Finally, the response data filtered by data operation scope and locked by data operation permissions can be confirmed as the target response data, achieving deep coupling between knowledge graph query and access control, and improving the data security of financial data in intelligent question-and-answer scenarios.

[0084] Figure 5This is a flowchart of a financial business problem processing method provided in the embodiments of this application, such as... Figure 5 As shown, it includes: at the data source layer, data is collected from multiple systems (e.g., core account system, financial management system and other platforms) and integrated through a dynamic data stitching engine; at the intelligent hub, a pension knowledge graph is constructed based on the integrated data and ambiguous terms are processed through a terminology disambiguation module; at the application layer, intelligent question answering is performed by connecting to an intelligent question answering interface, and reports are generated through an automated report generator.

[0085] Figure 6 This is a flowchart of a financial business problem provided according to an embodiment of this application, such as... Figure 6 As shown, for inquiries about early redemption of pension-related financial products, disambiguation can be performed to determine whether the inquiry is related to a product operation scenario or an account operation scenario. Different operation scenarios can correspond to different operation codes, and the question-and-answer process of financial products can be marked using operation codes.

[0086] In this embodiment, by integrating a knowledge graph of pension business data from multiple data sources, inquiries about pension business are answered. This avoids the situation where fragmented pension business knowledge leads to low efficiency in locating the knowledge required to answer pension questions, thereby achieving the technical effect of improving the efficiency of answering pension inquiries.

[0087] 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, and 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.

[0088] Example 2

[0089] This application also provides a processing apparatus for financial business problems. It should be noted that this processing apparatus for financial business problems can be used to execute the processing method for financial business problems provided in this application. The processing apparatus for financial business problems provided in this application is described below.

[0090] According to an embodiment of this application, an apparatus for implementing the above-described processing method for financial business problems is also provided, such as... Figure 7 As shown, the device includes: a receiving unit 71, a first processing unit 72, an acquisition unit 73, and a second processing unit 74.

[0091] The system includes a receiving unit 71 for receiving financial business questions from the target object, including questions related to pension business; a first processing unit 72 for standardizing the financial business questions to obtain standard business questions; an acquisition unit 73 for acquiring data access permissions from the target object, including access permissions to business data related to pension business; and a second processing unit 74 for determining target response data based on the standard business questions and data access permissions using a target knowledge graph, and visualizing the target response data. The target knowledge graph includes a knowledge graph constructed based on pension business-related data from M data sources, where M is a positive integer.

[0092] In the processing apparatus for financial business issues provided in this application embodiment, a receiving unit 71 can receive financial business issues from a target object, including issues related to pension business. A first processing unit 72 standardizes the financial business issues to obtain standard business issues. An acquisition unit 73 acquires data access permissions for the target object, including access permissions to pension business data. A second processing unit 74, based on the standard business issues and data access permissions, uses a target knowledge graph to determine target response data and visualizes the target response data. The target knowledge graph comprises a knowledge graph constructed based on pension business-related data from M data sources, where M is a positive integer. This solves the technical problem in related technologies where scattered pension business knowledge leads to low efficiency in responding to pension issues. In this embodiment, by integrating a knowledge graph of pension business data from multiple data sources to respond to pension business inquiries, the scattered pension business knowledge avoids the situation where low efficiency in locating pension issue response knowledge is caused by scattered pension business knowledge, thereby achieving the technical effect of improving the response efficiency of pension inquiry questions.

[0093] Optionally, in the processing apparatus for financial business problems provided in this application embodiment, the M data sources include: a financial system and a target file. The data in the target file includes at least one of the following: regulatory requirements and business rules for pension business. The target knowledge graph is obtained through the following sub-units: a first extraction sub-unit, used to extract structured data from the database of the financial system to obtain first business data; a second extraction sub-unit, used to extract unstructured data from the target file to obtain second business data; a third extraction sub-unit, used to extract entities from the first and second business data to obtain S entities, wherein the categories of the S entities include at least one of the following: product entities, operation entities, and rule entities, and S is a positive integer; a determination sub-unit, used to identify the relationships between the S entities and determine the data source of each relationship to obtain a target relationship set; and a construction sub-unit, used to construct the target knowledge graph based on the S entities and the target relationship set.

[0094] Optionally, in the processing apparatus for financial business problems provided in the embodiments of this application, the determining sub-unit includes: a construction module, used to construct nodes representing each entity to obtain S nodes; and an establishment module, used to establish connection edges between the S nodes based on the association relationships in the target relationship set and the data source of each association relationship to obtain a target knowledge graph.

[0095] Optionally, in the processing apparatus for financial business issues provided in this application embodiment, the second processing unit includes: an identification subunit for identifying the sensitivity level of the financial business issue and obtaining the target sensitivity level; an acquisition subunit for acquiring visualization rules, wherein the visualization rules include at least one of the following: chart type rules and style specifications; and a display subunit for visually displaying the target response data based on the target sensitivity level and the visualization rules.

[0096] Optionally, in the processing apparatus for financial business issues provided in this application embodiment, the identification subunit includes: an acquisition module, used to acquire all sensitive words associated with each of the S sensitivity levels to obtain S sensitive word sets; an identification module, used to identify whether the financial business issue contains any sensitive word from each sensitive word set to obtain an identification result; and a determination module, used to determine the sensitivity level associated with the sensitive word set as the target sensitivity level if the financial business issue contains any sensitive word from the sensitive word set.

[0097] Optionally, in the processing apparatus for financial business issues provided in this application embodiment, the display subunit includes: a first processing module, used to perform desensitization processing on the target response data when the target sensitivity level is the first sensitivity level, to obtain desensitized target response data, and to visualize the desensitized target response data based on visualization rules; a second processing module, used to add a watermark to the target response data when the target sensitivity level is the second sensitivity level, to obtain watermarked target response data, and to visualize the watermarked target response data based on visualization rules; and a display module, used to visualize the target response data based on visualization rules when the target sensitivity level is the third sensitivity level.

[0098] Optionally, in the processing apparatus for financial business issues provided in this application embodiment, the data access permission includes at least one of the following: data access scope and data operation permission. The second processing unit includes: an extraction subunit, used to extract data from the target knowledge graph based on a standard business question to obtain first response data; a filtering subunit, used to filter the first response data based on the data access scope to obtain second response data; and a processing subunit, used to set the operation permission of the second response data based on the data operation permission, and determine the second response data with the set operation permission as the target response data.

[0099] It should be noted that the receiving unit 71, the first processing unit 72, the acquiring unit 73, and the second processing unit 74 mentioned above correspond to steps S201 to S204 in Embodiment 1. Each unit and the corresponding step implement the same instance and application scenario, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above modules can also be part of the device and run in the computer terminal 10 provided in Embodiment 1.

[0100] Example 3

[0101] Embodiments of this application may provide an electronic device. Figure 8 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 8 As shown, the electronic device may include: one or more ( Figure 8 (Only one is shown) processor 802, memory 804, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0102] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, 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.

[0103] The processor can invoke information and applications stored in the memory via a transmission device to perform the following steps: receiving financial business questions from the target object, wherein the financial business questions include questions related to pension business; standardizing the financial business questions to obtain standard business questions; acquiring data access permissions from the target object, wherein the data access permissions include access permissions to business data related to pension business; based on the standard business questions and data access permissions, determining the target response data using a target knowledge graph, and visualizing the target response data, wherein the target knowledge graph includes a knowledge graph constructed based on pension business-related data from M data sources, where M is a positive integer.

[0104] The processor can also invoke information and applications stored in the memory via a transmission device to execute the following steps: M data sources include: a financial system and target files. The data in the target files includes at least one of the following: regulatory requirements and business rules for pension business. The target knowledge graph is obtained by: extracting structured data from the database of the financial system to obtain first business data; extracting unstructured data from the target files to obtain second business data; extracting entities from the first and second business data to obtain S entities, where the categories of the S entities include at least one of the following: product entities, operation entities, and rule entities, where S is a positive integer; identifying the relationships between the S entities and determining the data source for each relationship to obtain a target relationship set; and constructing a target knowledge graph based on the S entities and the target relationship set.

[0105] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: constructing a target knowledge graph based on S entities and a target relation set, including: constructing nodes representing each entity to obtain S nodes; establishing connection edges between the S nodes based on the associations in the target relation set and the data source of each association to obtain the target knowledge graph.

[0106] The processor can also invoke information and applications stored in the memory via a transmission device to perform the following steps: visualizing the target response data, including: identifying the sensitivity level of financial business issues and obtaining the target sensitivity level; obtaining visualization rules, wherein the visualization rules include at least one of the following: chart type rules and style specifications; and visualizing the target response data based on the target sensitivity level and visualization rules.

[0107] The processor can also call the information and application programs stored in the memory through the transmission device to perform the following steps: identify the sensitivity level of the financial business issue and obtain the target sensitivity level, including: obtaining all sensitive words associated with each of the S sensitivity levels to obtain S sensitive word sets; identifying whether the financial business issue contains any of the sensitive words in each sensitive word set to obtain the identification result; and determining the sensitivity level associated with the sensitive word set as the target sensitivity level if the financial business issue contains any of the sensitive words in the sensitive word set.

[0108] The processor can also access information and applications stored in the memory via a transmission device to perform the following steps: visualizing the target response data based on the target sensitivity level and visualization rules, including: when the target sensitivity level is the first sensitivity level, desensitizing the target response data to obtain desensitized target response data, and visualizing the desensitized target response data based on visualization rules; when the target sensitivity level is the second sensitivity level, adding a watermark to the target response data to obtain watermarked target response data, and visualizing the watermarked target response data based on visualization rules; when the target sensitivity level is the third sensitivity level, visualizing the target response data based on visualization rules.

[0109] The processor can also invoke information and applications stored in the memory via a transmission device to perform the following steps: Data access permissions include at least one of the following: data access scope, data operation permissions; based on standard business questions and data access permissions, using a target knowledge graph, determine target response data, including: extracting data from the target knowledge graph based on standard business questions to obtain first response data; filtering the first response data based on the data access scope to obtain second response data; setting operation permissions for the second response data based on data operation permissions, and determining the second response data with set operation permissions as the target response data.

[0110] By employing the embodiments of this application, a knowledge graph integrating pension business data from multiple data sources is used to answer inquiries about pension business. This avoids the situation where fragmented pension business knowledge leads to low efficiency in locating the knowledge required to answer pension questions, thereby achieving the technical effect of improving the efficiency of answering pension inquiries.

[0111] Those skilled in the art will understand that Figure 8 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 8 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 8 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 8 The different configurations shown.

[0112] Those skilled in the art will understand that all or part of the steps in the various methods of 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.

[0113] Example 4

[0114] 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 processing method for financial business problems provided in Embodiment 1.

[0115] 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.

[0116] This application also provides a computer program product that, when executed on a data processing device, is suitable for performing processing method steps for financial business problems.

[0117] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0118] In the above embodiments of this application, 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.

[0119] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, 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 between units or modules may be electrical or other forms.

[0120] 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 network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0121] Furthermore, the functional units in the various embodiments of this application 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.

[0122] 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 this application, 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 this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0123] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for handling financial business problems, characterized in that, include: Receive financial business questions from the target object, wherein the financial business questions include: questions related to pension business; The financial business problem is standardized to obtain the standard business problem; Obtain data access permissions for the target object, wherein the data access permissions include: access permissions to the business data of the pension business; Based on the standard business question and the data access permissions, target response data is determined using a target knowledge graph, and the target response data is visualized. The target knowledge graph includes a knowledge graph constructed based on data related to the pension business from M data sources, where M is a positive integer.

2. The processing method according to claim 1, characterized in that, The M data sources include: financial systems and target files. The data in the target files includes at least one of the following: regulatory requirements and business rules for the pension fund business. The target knowledge graph is obtained through the following methods: Data is extracted from the structured data in the database of the financial system to obtain the first business data; Data extraction is performed on the unstructured data in the target file to obtain the second business data; Entities are extracted from the first business data and the second business data to obtain S entities, wherein the categories of the S entities include at least one of the following: product entities, operation entities, and rule entities, and S is a positive integer; Identify the relationships between the S entities and determine the data source for each relationship to obtain the target relationship set; Based on the S entities and the target relationship set, construct the target knowledge graph.

3. The processing method according to claim 2, characterized in that, Based on the S entities and the target relation set, the target knowledge graph is constructed, including: Construct nodes representing each of the entities to obtain S nodes; Based on the associations in the target relation set and the data source of each association, establish connection edges between S nodes to obtain the target knowledge graph.

4. The processing method according to claim 1, characterized in that, Visualizing the target response data includes: Identify the sensitivity level of the financial business issue to obtain the target sensitivity level; Obtain visualization rules, wherein the visualization rules include at least one of the following: chart type rules, style specifications; Based on the target sensitivity level and the visualization rules, the target response data is visualized.

5. The processing method according to claim 4, characterized in that, Identify the sensitivity level of the aforementioned financial business issue to obtain the target sensitivity level, including: Obtain all sensitive words associated with each of the S sensitivity levels to obtain S sets of sensitive words; The identification results are obtained by identifying whether the financial business question contains sensitive words from each of the sensitive word sets. If the financial business issue contains any of the sensitive words in the set of sensitive words, the sensitivity level associated with the set of sensitive words shall be determined as the target sensitivity level.

6. The processing method according to claim 4, characterized in that, Based on the target sensitivity level and the visualization rules, the target response data is visualized, including: When the target sensitivity level is the first sensitivity level, the target response data is de-identified to obtain de-identified target response data, and the de-identified target response data is visualized based on the visualization rules. When the target sensitivity level is the second sensitivity level, a watermark is added to the target response data to obtain watermarked target response data, and the watermarked target response data is visualized based on the visualization rules. When the target sensitivity level is the third sensitivity level, the target response data is visualized based on the visualization rules.

7. The processing method according to claim 1, characterized in that, The data access permissions include at least one of the following: data access scope, data operation permissions. Based on the standard business question and the data access permissions, the target response data is determined using the target knowledge graph, including: Based on the standard business question, data is extracted from the target knowledge graph to obtain the first response data; The first response data is filtered based on the data access range to obtain the second response data; Based on the data operation permissions, the operation permissions for the second response data are set, and the second response data with the set operation permissions is determined as the target response data.

8. A processing device for financial business problems, characterized in that, include: A receiving unit is used to receive financial business questions from a target object, wherein the financial business questions include questions related to pension business. The first processing unit is used to standardize the financial business problem to obtain a standard business problem. An acquisition unit is used to acquire data access permissions for the target object, wherein the data access permissions include: access permissions to business data of the pension business; The second processing unit is used to determine the target response data based on the standard business question and the data access permissions using the target knowledge graph, and to visualize the target response data. The target knowledge graph includes a knowledge graph constructed based on data related to the pension business from M data sources, where M is a positive integer.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the processing method for financial business problems as described in any one of claims 1 to 7.

10. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the processing method for financial business problems as described in any one of claims 1 to 7.

Images