Method, device and equipment for analyzing business data and computer readable medium

Abstract

The invention discloses a method, a device and equipment for analyzing business data and a computer readable medium, and relates to the technical field of big data. A specific embodiment of the method comprises the following steps: modifying errors in original business data and identifying key business data in the original business data by utilizing a large language model, and dividing the modified original business data into a plurality of data categories according to the key business data; in the business data in the data category, acquiring an association relationship between entities by adopting a large language model so as to acquire a business constraint condition of the business data; and establishing an entity relationship model based on the association relationship between the entities, identifying the entities in the entity relationship model by using the business constraint conditions, filling the entity relationship model according to the business data in the data category to obtain a data analysis model, and inputting the current business data into the data analysis model to obtain an analysis result of the current business data. According to the embodiment, the business data analysis efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and in particular to a method, device, equipment and computer-readable medium for analyzing business data. Background Art

[0002] In the operation and management of contemporary enterprises, the role of data is becoming increasingly prominent and has become a key asset to enhance the competitiveness and core value of enterprises. Enterprises accumulate a large amount of data in the daily operation process. These data are scattered in different business systems, such as human resource management system, financial management system and project management system, covering a wide range of data from customer information, financial data to project details.

[0003] In the process of implementing the present invention, the inventors found that there are at least the following problems in the prior art: since the business data involved in the daily operation of the enterprise is huge, the efficiency of analyzing the business data is low. Summary of the invention

[0004] In view of this, embodiments of the present invention provide a method, apparatus, device and computer-readable medium for analyzing business data, which can improve the efficiency of analyzing business data.

[0005] To achieve the above object, according to one aspect of an embodiment of the present invention, a method for analyzing business data is provided, comprising:

[0006] Using a large language model to modify errors in the original business data and identify key business data in the original business data, and dividing the modified original business data into multiple data categories according to the key business data;

[0007] In the business data in the data category, the large language model is used to obtain the association relationship between entities, and the temporal relationship between the entities and the causal relationship between the entities are screened out according to the association relationship to obtain the business constraint conditions of the business data;

[0008] An entity relationship model is established based on the association relationship between the entities, the entities in the entity relationship model are identified by the business constraints, and the entity relationship model is filled with the business data in the data category to obtain a data analysis model, and the current business data is input into the data analysis model to obtain an analysis result of the current business data.

[0009] The method of using the large language model to modify errors in the original business data and identify key business data in the original business data, and dividing the modified original business data into multiple data categories according to the key business data, includes:

[0010] After modifying the errors in the original business data using the large language model, identifying key business data in the original business data in the modified original business data;

[0011] The data format of the modified original business data is standardized to obtain standardized business data, and the standardized business data is divided into multiple data categories according to the key business data using the large speech model.

[0012] In the business data in the data category, the large language model is used to obtain the association relationship between entities, and the temporal relationship between the entities and the causal relationship between the entities are screened out according to the association relationship to obtain the business constraints of the business data, including:

[0013] In the business data in the data category, the large language model is used to obtain the association relationship between entities;

[0014] The large language model is used to screen out the temporal relationship between the entities and the causal relationship between the entities in the association relationship, and the temporal relationship between the entities and the causal relationship between the entities are analyzed to obtain the business constraints of the entities.

[0015] The method further comprises:

[0016] Financial entities and relationships between financial entities are extracted from a database of financial business data, a financial domain ontology library is constructed, and the large language model is obtained by training using the financial domain ontology library.

[0017] The step of establishing an entity relationship model based on the association relationship between the entities, identifying entities in the entity relationship model with the business constraint conditions, filling the entity relationship model with the business data in the data category to obtain a data analysis model, and inputting current business data into the data analysis model to obtain an analysis result of the current business data includes:

[0018] Establishing an entity relationship model according to the association relationship between the entities, and identifying the entities in the entity relationship model with the business constraint conditions;

[0019] Analyze business data according to the data category to obtain regional business data and product business data, fill the entity relationship model with the regional business data and the product business data to obtain a data analysis model, and input current business data into the data analysis model to obtain the analysis result of the current business data.

[0020] The step of inputting the current business data into the data analysis model to obtain the analysis result of the current business data includes:

[0021] The current business data includes current customer data and / or current product data. The current business data is input into the data analysis model to obtain the analysis results of the current business data. The analysis results of the current business data include current customer risk analysis results and / or current product business indicator analysis results.

[0022] After filling the entity relationship model according to the business data in the data category to obtain the data analysis model, the method further includes:

[0023] The data analysis model is updated by one or more of updating entities, updating attribute fields of business data, and updating business constraints.

[0024] According to a second aspect of an embodiment of the present invention, there is provided a device for analyzing business data, including:

[0025] A processing module, used to modify errors in the original business data and identify key business data in the original business data using a large language model, and divide the modified original business data into multiple data categories according to the key business data;

[0026] A conditional module, used to obtain the association relationship between entities in the business data in the data category using the large language model, and screen out the temporal relationship between the entities and the causal relationship between the entities according to the association relationship, so as to obtain the business constraint conditions of the business data;

[0027] An analysis module is used to establish an entity relationship model based on the association relationship between the entities, identify the entities in the entity relationship model with the business constraints, fill the entity relationship model with the business data in the data category to obtain a data analysis model, and input the current business data into the data analysis model to obtain the analysis results of the current business data.

[0028] According to a third aspect of an embodiment of the present invention, there is provided an electronic device for analyzing business data, including:

[0029] one or more processors;

[0030] a storage device for storing one or more programs,

[0031] When the one or more programs are executed by the one or more processors, the one or more processors implement the above method.

[0032] According to a fourth aspect of an embodiment of the present invention, there is provided a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the method as described above is implemented.

[0033] According to a fifth aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, and when the program is executed by a processor, the method as described above provided by an embodiment of the present invention is implemented.

[0034] One embodiment of the above invention has the following advantages or beneficial effects: using a large language model to modify errors in the original business data and identify key business data in the original business data, and dividing the modified original business data into multiple data categories according to the key business data; in the business data in the data category, using the large language model to know the association relationship between entities, and according to the association relationship, filtering out the temporal relationship between the entities and the causal relationship between the entities, so as to know the business constraints of the business data; establishing an entity relationship model based on the association relationship between the entities, identifying the entities in the entity relationship model with the business constraints, and filling the entity relationship model according to the business data in the data category to obtain a data analysis model, and inputting the current business data into the data analysis model to obtain the analysis result of the current business data. The data analysis model is established on the basis of the original business data, and can improve the efficiency of analyzing business data without manual intervention.

[0035] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0037] Figure 1 is a schematic diagram of the main flow of a method for analyzing business data according to an embodiment of the present invention;

[0038] Figure 2 is a schematic diagram of a process of processing original business data using a large language model according to an embodiment of the present invention;

[0039] Figure 3 is a schematic diagram of a process of obtaining a service constraint condition of service data according to an embodiment of the present invention;

[0040] Figure 4 is a schematic diagram of a process for obtaining a data analysis model according to an embodiment of the present invention;

[0041] Figure 5 is a schematic diagram of the main structure of a device for analyzing business data according to an embodiment of the present invention;

[0042] Figure 6 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0043] Figure 7It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0044] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description. The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0045] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0046] Enterprises accumulate a large amount of business data in their daily operations, and these business data are scattered in different business systems. If these data assets can be effectively integrated and analyzed, it will greatly improve the internal management level of the enterprise and the quality of project execution. However, the dispersion and heterogeneity of business data have brought many challenges to the unified management and efficient use of data assets.

[0047] At present, data warehouses and data lakes are mostly used to process business data in business systems.

[0048] Data warehouse is to realize the integration of data assets by building a data warehouse that centrally stores, processes and manages internal and external data of an enterprise. It uses the process of extraction, transformation and loading to process and integrate data to ensure the consistency and queryability of data. However, data warehouse technology has limitations in processing unstructured data and real-time data streams.

[0049] Data lakes are designed to store large amounts of raw data, both structured and unstructured, and retain it in its original format until it is needed for processing. This provides greater flexibility and scalability, but introduces new challenges in terms of data quality control and governance.

[0050] The following technical problems are often encountered when processing business data by building models:

[0051] First, the model building efficiency is low. Data model building is a complex and time-consuming process that requires a lot of manual participation. From data collection and cleaning to model design, each step has a high time cost and is not easy to quickly iterate and optimize.

[0052] Secondly, the model is not adaptable enough. Fixed templates are often used to build data models, which are difficult to adapt to the complex and changing business needs of enterprises. When business processes or data sources change, the model often cannot adapt flexibly, affecting the real-time and accuracy of enterprise decision-making.

[0053] Furthermore, the model is updated slowly. As the amount of data increases and business requirements change, the data model needs to be updated regularly to reflect the latest situation. When the model is updated, it is usually necessary to re-design and deploy the model, which is not only time-consuming but also inefficient.

[0054] In summary, due to the huge amount of business data involved in daily operations, the efficiency of analyzing business data is low.

[0055] In order to solve the low efficiency of analyzing business data, the following technical solution in the embodiment of the present invention can be adopted.

[0056] See also Figure 1 , Figure 1 1 is a schematic diagram of the main flow of the method for analyzing business data according to an embodiment of the present invention, which realizes timely analysis of current business data by establishing a data analysis model. Figure 1 As shown in 100, the following steps are specifically included:

[0057] S101. Use a large language model to modify errors in original business data and identify key business data in the original business data, and divide the modified original business data into multiple data categories according to the key business data.

[0058] The large language model is a deep learning algorithm in the field of artificial intelligence, which can perform various natural language processing tasks. In an embodiment of the present invention, a data analysis model is constructed using a large language model, and then the data analysis model is used to analyze the current business data.

[0059] There are erroneous data, incomplete data, inconsistent data, duplicate data, etc. in the original business data. In an embodiment of the present invention, a large language model is used to modify the errors in the original business data. Then, key business data in the original business data is identified. The modified original business data is divided into multiple data categories according to the key business data.

[0060] See also Figure 2 That is 200, Figure 2This is a flow chart of processing original business data using a large language model according to an embodiment of the present invention. Specifically, it includes the following steps:

[0061] S201. After modifying errors in original business data using a large language model, key business data in the modified original business data is identified.

[0062] The original business data is input into the big language model, and the big language model automatically corrects the errors in the original business data according to the context of the original business data. As an example, the spelling errors in the original business data are corrected, and the synonyms in the original business data are corrected, such as: synonyms are uniformly replaced with the same word.

[0063] After correcting the errors in the original business data, the large language model can also be used to identify key business data in the modified original business data. As an example, the key business data includes: deposit amount, amount of financial products purchased, and number of financial products held.

[0064] S202, standardize the modified data format of the original business data to obtain standardized business data, and use a large voice model to divide the standardized business data into multiple data categories according to key business data.

[0065] In the financial field, the original business data includes date data and currency data. In order to improve the efficiency of processing business data, the data format of the original business data is standardized and modified to obtain standardized business data. The big language model can deeply understand the semantics of data content, and the big voice model is used to divide the standardized business data into multiple data categories according to key business data.

[0066] Key business data is the core of business data. Standardized business data is divided into multiple data categories according to key business data. Each data category reflects a type of key business data. For example, data categories include deposit data, financial product purchase data, and financial product holding data.

[0067] exist Figure 2 In the embodiment, the natural language understanding ability of the large language model is fully utilized to identify and modify errors in the original business data, and the original business data is divided into multiple data categories to achieve efficient processing of the original business data.

[0068] In one embodiment of the present invention, the original business data includes personal business data and corporate business data. Personal business data includes personal customer information and personal transaction data. Corporate business data includes corporate customer information, corporate financing data and corporate cash management data. Among them, personal business data and corporate business data can be obtained in the following systems: core transaction system, online banking system and financial sales system.

[0069] In one embodiment of the present invention, considering that the big language model is a general model, in order to improve the pertinence and adaptability of the big language, financial business data can be used for training to obtain a big language model suitable for the financial field.

[0070] Extract the relationships between financial entities in the database of financial business data, build a financial domain ontology library, and use the financial domain ontology library to train a large language model.

[0071] Specifically, natural language processing technology is used to identify financial entities in the database of financial business data. As an example, financial entities include: individuals, companies, products and events. As an example, the business data of the bank's core business system, financial sales system, risk control system and customer relationship management system are used as the database of financial business data.

[0072] Secondly, extract the relationship between financial entities in the database of financial business data and build a financial domain ontology library. As an example, the relationship between financial entities includes: ownership relationship, transaction relationship and cooperation relationship. The financial domain ontology library includes financial entities and the knowledge graph constructed by the relationship between financial entities. The financial domain ontology library can be used to store, query and reason about knowledge in the financial field.

[0073] The large language model is trained using the financial domain ontology library. By learning the financial entities in the financial domain ontology library and the relationships between financial entities, the large language model can skillfully understand and apply financial business terms and concepts, thereby improving the effectiveness of processing business data in the financial field.

[0074] The trained large language model already contains a lot of professional knowledge, which can better understand the professional terms, professional concepts and data patterns in the professional field. For example, the large language model is trained using the medical field ontology library. The large language model can accurately identify professional concepts such as diagnosis names, surgical codes, and medication specifications and their relationships.

[0075] S102. In the business data in the data category, a large language model is used to obtain the association relationship between entities, and the temporal relationship between entities and the causal relationship between entities are screened out according to the association relationship to obtain the business constraints of the business data.

[0076] In the embodiment of the present invention, the large language model has a powerful natural language understanding ability and can identify the implicit relationship between data. For the business data in the data category, the large language model is used to obtain the association relationship between entities, and the temporal relationship between entities and the causal relationship between entities are screened according to the association relationship to obtain the business constraints of the business data.

[0077] See also Figure 3 That is 300, Figure 3 The figure is a schematic diagram of a process of obtaining a service constraint condition of service data according to an embodiment of the present invention.

[0078] S301. In the business data in the data category, a large language model is used to obtain the relationship between entities.

[0079] In the embodiment of the present invention, the business constraint of the business data can be obtained from the business data in a data category. It can be understood that the business constraint is related to the data category, that is, the business constraint is the business constraint corresponding to the data category.

[0080] Specifically, in the business data in the data category, the large language model is used to obtain the association relationship between entities. As an example, in the data category: employee, the large language model is used to identify the entities: employee ID, department, rank and salary. The large language model is used to obtain the association relationship between entities, and the association relationship between entities includes: department includes employee ID, department includes rank. Employee ID corresponds to rank and work.

[0081] S302: Filter out the temporal relationship and the causal relationship between entities in the association relationship by using the large language model, and analyze the temporal relationship and the causal relationship between entities to obtain the business constraints of the entities.

[0082] The association relationships between entities include the temporal relationships between entities and the causal relationships between entities. The large language model can be used to screen out the temporal relationships between entities and the causal relationships between entities in the association relationships.

[0083] As an example, the data category includes financial transactions. The association relationships between entities include: transaction time and revenue data; market conditions and revenue data; trading strategies and revenue data. Among them, the temporal relationship between entities includes: transaction time and revenue data; the causal relationship between entities includes: market conditions and revenue data, trading strategies and revenue data.

[0084] The business constraints of entities are obtained by analyzing the temporal relationship and causal relationship between entities through the big language model. As an example, the data category includes human resources. The business constraints of entities obtained through the big language model analysis include: employee rank promotion constraints and employee salary increase constraints.

[0085] exist Figure 3In the embodiment, the relationship between entities is analyzed through a large language model to obtain business constraints of the entities. Business constraints are logic that can be implemented in a large language model, laying a solid foundation for building a high-quality data analysis model.

[0086] S103. Establish an entity relationship model based on the association relationship between entities, identify entities in the entity relationship model with business constraints, fill the entity relationship model with business data in the data category to obtain a data analysis model, and input the current business data into the data analysis model to obtain the analysis results of the current business data.

[0087] In an embodiment of the present invention, an entity relationship model is established based on the association relationship between entities, and then the entities in the entity relationship model are identified by business constraints, and the entity relationship model is filled with business data in the data category to obtain a data analysis model. The function of the data analysis model is to analyze the current business data. The current business data can be input into the data analysis model to obtain the analysis results of the current business data.

[0088] See also Figure 4 That is 400, Figure 4 1 is a flow chart of obtaining a data analysis model according to an embodiment of the present invention. Specifically, the following steps are included:

[0089] S401: Establish an entity relationship model according to the association relationship between entities, and identify entities in the entity relationship model with business constraints.

[0090] In an embodiment of the present invention, an entity relationship model is established according to the association relationship between entities. As an example, financial customers include two entities: individual customers and corporate customers. Individual customers are associated with account entities, corporate customers are associated with account entities, and account entities are associated with transaction entities. Furthermore, an entity relationship model is established according to the association relationship between the above entities.

[0091] The entity relationship model involves multiple entities, and the entities in the entity relationship model are identified by business constraints. As an example, the business constraints corresponding to the entities are identified between two entities. For example, the business constraints include customer risk rating rules, and the two entities include: individual customers and account entities. The business constraints include transaction anti-fraud rules, and the two entities include: corporate customers and account entities.

[0092] In one embodiment of the present invention, financial business data requires strict risk management and business control, which are achieved through business constraints. Business constraints include one or more of the following: transaction approval process conditions, risk limit control conditions, and anti-money laundering monitoring conditions.

[0093] S402, analyzing business data according to data categories to obtain regional business data and product business data, filling an entity relationship model with the regional business data and product business data to obtain a data analysis model, and inputting current business data into the data analysis model to obtain analysis results of the current business data.

[0094] In financial business data, analysis is mostly conducted from two dimensions: region and product. Business data can be analyzed according to data categories to obtain regional business data and product business data, and the entity relationship model can be filled with regional business data and product business data to obtain a data analysis model. After filling the data analysis model with regional business data and product business data, the entity hierarchy and relationship structure can be improved.

[0095] In one embodiment of the present invention, after the data analysis model is constructed, in order to ensure the validity of the data analysis model, the data analysis model can be tested with data, and the current business data can be directly processed by the tested data analysis model.

[0096] As an example, the data analysis model is loaded into a data warehouse or a big data platform, and the business applicability of the data analysis model is verified through the test data in the data warehouse or the big data platform. For example, the test data in the data warehouse or the big data platform is input into the data analysis model, and the data analysis model outputs the analysis results of the test data. If the analysis results of the test data are consistent with the setting results of the test data, the data analysis model passes the test. If the analysis results of the test data are different from the setting results of the test data, the data analysis model needs to be re-established.

[0097] In one embodiment of the present invention, preset business data may also be filled into the entity relationship model to obtain a data analysis model.

[0098] For example, the preset business data includes account entry data and coding system data. As an example, the coding system can be an international standard, such as ISO 15459, or a system within a specific financial institution. By using account entry data and coding system data, the data analysis model supports complex account entries and coding systems. It can achieve refined accounting of accounts and prepare various reports in accordance with accounting standards and regulatory requirements.

[0099] exist Figure 4 In the embodiment, business constraints and business data are used to build and fill the entity relationship model to obtain the data analysis model, so as to improve the availability of the data analysis module.

[0100] In one embodiment of the present invention, the current business data includes current customer data and / or current product data. The current business data is input into a data analysis model to obtain analysis results of the current business data. The analysis results of the current business data include current customer risk analysis results and / or current product business indicator analysis results.

[0101] As an example, current customer data includes: account data, transaction data and basic customer data. Account data includes basic information of various personal accounts and corporate accounts. Transaction data includes various transaction details such as deposits and withdrawals, transfers, remittances and investment and financial management. Basic customer data includes: customer identity information, contact information and risk level, etc.

[0102] Current product data includes: product information data and auxiliary data. Product information data includes: parameter information of various deposits, loans, funds and other products. Auxiliary data includes: interest rate data, internal and external accounting subjects and account data, etc.

[0103] The current customer risk analysis results include: customer-level risk assessment results and marketing initiative scores. The marketing initiative score is an indicator for evaluating and predicting the effectiveness of marketing activities.

[0104] The current product business indicator analysis results include: business indicator analysis results by product line, department, region and other dimensions; various regulatory reports, such as balance sheet, profit and loss statement, etc.; internal management reports, such as employee performance appraisal report, etc.; credit risk model, providing risk verification support for loan approval; monitoring and early warning results of abnormal transaction behavior

[0105] Through the current customer risk analysis results and / or the current product business indicator analysis results, the data analysis model can fully support the analysis needs of business decision-making and risk management.

[0106] In one embodiment of the present invention, as business data continues to increase and business develops, the data analysis model needs to be updated to adapt to new businesses and newly added business data. The data analysis model is updated by updating one or more of entities, updating attribute fields of business data, and updating business constraints. The updated data analysis model is always kept up to date and can effectively support enterprise decision-making and operation management.

[0107] As an example, the financial industry is greatly affected by regulatory policies, such as deposit reserve ratio, interest rate policy, anti-money laundering, etc. When adjustments are made, business constraints are updated accordingly. Business constraints include: accounting constraints and risk control constraints.

[0108] As an example, when the data source changes, update the entity and update the attribute fields of the business data.

[0109] As an example, due to changes in business policies or assessment methods, attribute fields of business data are added or modified.

[0110] In the above-mentioned embodiment of the present invention, a large language model is used to modify errors in the original business data and identify key business data in the original business data, and the modified original business data is divided into multiple data categories according to the key business data; in the business data in the data category, the large language model is used to obtain the association relationship between entities, and the temporal relationship between the entities and the causal relationship between the entities are screened out according to the association relationship to obtain the business constraints of the business data; an entity relationship model is established based on the association relationship between the entities, the entities in the entity relationship model are identified by the business constraints, and the entity relationship model is filled according to the business data in the data category to obtain a data analysis model, and the current business data is input into the data analysis model to obtain the analysis result of the current business data. The data analysis model is established on the basis of the original business data, and the efficiency of analyzing business data can be improved without human intervention.

[0111] The technical solution in the embodiment of the present invention is adopted to support enterprises to gain insight into business opportunities in massive data, make more accurate decisions, promote the optimization of internal enterprise processes and improve management efficiency, and ultimately enhance the core competitiveness of the enterprise.

[0112] See also Figure 5 , Figure 5 is a schematic diagram of the main structure of an apparatus for analyzing business data according to an embodiment of the present invention. The apparatus for analyzing business data can implement a method for analyzing business data, such as Figure 5 As shown in 500, the device for analyzing business data specifically includes:

[0113] Processing module 501, used to modify errors in original business data and identify key business data in the original business data using a large language model, and divide the modified original business data into multiple data categories according to the key business data;

[0114] A condition module 502 is used to obtain the association relationship between entities in the business data in the data category using the large language model, and filter out the temporal relationship between the entities and the causal relationship between the entities according to the association relationship to obtain the business constraint conditions of the business data;

[0115] The analysis module 503 is used to establish an entity relationship model based on the association relationship between the entities, identify the entities in the entity relationship model with the business constraints, fill the entity relationship model with the business data in the data category to obtain a data analysis model, and input the current business data into the data analysis model to obtain the analysis results of the current business data.

[0116] In one embodiment of the present invention, the processing module 501 is specifically configured to identify key business data in the original business data after modifying errors in the original business data using the large language model;

[0117] The data format of the modified original business data is standardized to obtain standardized business data, and the standardized business data is divided into multiple data categories according to the key business data using the large speech model.

[0118] In one embodiment of the present invention, the condition module 502 is specifically used to use the large language model to obtain the association relationship between entities in the business data in the data category;

[0119] The large language model is used to screen out the temporal relationship between the entities and the causal relationship between the entities in the association relationship, and the temporal relationship between the entities and the causal relationship between the entities are analyzed to obtain the business constraints of the entities.

[0120] In one embodiment of the present invention, the processing module 501 is further used to extract financial entities and the relationships between financial entities in a database of financial business data, construct a financial domain ontology library, and use the financial domain ontology library to train and obtain the large language model.

[0121] In one embodiment of the present invention, the analysis module 503 is specifically used to establish an entity relationship model according to the association relationship between the entities, and identify the entities in the entity relationship model with the business constraint conditions;

[0122] Analyze business data according to the data category to obtain regional business data and product business data, fill the entity relationship model with the regional business data and the product business data to obtain a data analysis model, and input current business data into the data analysis model to obtain the analysis result of the current business data.

[0123] In one embodiment of the present invention, the analysis module 503 is specifically used for the current business data including current customer data and / or current product data, inputting the current business data into the data analysis model to obtain the analysis results of the current business data, and the analysis results of the current business data include current customer risk analysis results and / or current product business indicator analysis results.

[0124] In one embodiment of the present invention, the analysis module 503 is specifically used to update the data analysis model by using one or more of updating entities, updating attribute fields of business data, and updating business constraints.

[0125] Figure 6 An exemplary system architecture 600 is shown to which the method for analyzing business data or the apparatus for analyzing business data according to the embodiments of the present invention can be applied.

[0126] like Figure 6 As shown, system architecture 600 may include terminal devices 601, 602, 603, network 604 and server 605. Network 604 is used to provide a medium for communication links between terminal devices 601, 602, 603 and server 605. Network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0127] The user can use the terminal devices 601, 602, 603 to interact with the server 605 through the network 604 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 601, 602, 603, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only for example).

[0128] The terminal devices 601 , 602 , and 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0129] The server 605 may be a server that provides various services, such as a backend management server (only an example) that provides support for shopping websites browsed by users using the terminal devices 601, 602, and 603. The backend management server may analyze and process the received data such as product information query requests, and feed back the processing results (such as target push information, product information - only an example) to the terminal device.

[0130] It should be noted that the method for analyzing business data provided in the embodiment of the present invention is generally executed by the server 605 , and accordingly, the device for analyzing business data is generally set in the server 605 .

[0131] It should be understood that Figure 6 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0132] A computer program product according to an embodiment of the present invention includes a computer program, and when the program is executed by a processor, the method for analyzing business data provided by the embodiment of the present invention is implemented.

[0133] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system 700 of a terminal device suitable for implementing an embodiment of the present invention. Figure 7 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0134] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other through a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0135] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0136] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present invention are executed.

[0137] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0138] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0139] The modules involved in the embodiments of the present invention may be implemented in software or hardware. The modules described may also be arranged in a processor, for example, they may be described as: a processor including a processing module, a conditional module and an analysis module. The names of these modules do not constitute limitations on the modules themselves in certain cases, for example, the processing module may also be described as "used to modify errors in the original business data and identify key business data in the original business data using a large language model, and divide the modified original business data into multiple data categories according to the key business data".

[0140] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes:

[0141] Using a large language model to modify errors in the original business data and identify key business data in the original business data, and dividing the modified original business data into multiple data categories according to the key business data;

[0142] In the business data in the data category, the large language model is used to obtain the association relationship between entities, and the temporal relationship between the entities and the causal relationship between the entities are screened out according to the association relationship to obtain the business constraint conditions of the business data;

[0143] An entity relationship model is established based on the association relationship between the entities, the entities in the entity relationship model are identified by the business constraints, and the entity relationship model is filled with the business data in the data category to obtain a data analysis model, and the current business data is input into the data analysis model to obtain an analysis result of the current business data.

[0144] According to the technical solution of the embodiment of the present invention, a large language model is used to modify errors in the original business data and identify key business data in the original business data, and the modified original business data is divided into multiple data categories according to the key business data; in the business data in the data category, the large language model is used to obtain the association relationship between entities, and the temporal relationship between the entities and the causal relationship between the entities are screened out according to the association relationship to obtain the business constraints of the business data; an entity relationship model is established based on the association relationship between the entities, the entities in the entity relationship model are identified by the business constraints, and the entity relationship model is filled according to the business data in the data category to obtain a data analysis model, and the current business data is input into the data analysis model to obtain the analysis result of the current business data. The data analysis model is established on the basis of the original business data, and the efficiency of analyzing business data can be improved without human intervention.

[0145] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0146] It should be noted that in the technical solution of the present invention, the collection, analysis, use, transmission, storage and other aspects of user personal information involved are in compliance with the provisions of relevant laws and regulations, are used for legal and reasonable purposes, are not shared, leaked or sold outside of these legal uses, and are subject to supervision and management by regulatory authorities. Necessary measures should be taken for user personal information to prevent illegal access to such personal information data, ensure that persons who have access to personal information data comply with the provisions of relevant laws and regulations, and ensure the security of user personal information. Once these user personal information data are no longer needed, the risks should be minimized by limiting or even prohibiting data collection and / or deleting data.

[0147] When applicable, including in certain relevant applications, protect user privacy by de-identifying data, such as by removing specific identifiers (e.g., date of birth, etc.) when applicable, controlling the amount or specificity of data stored (e.g., collecting location data at a city level rather than at a specific address level), controlling how data is stored, and / or other de-identification methods.

Claims

1. A method for analyzing business data, characterized in that: include: Using a large language model to modify errors in the original business data and identify key business data in the original business data, and dividing the modified original business data into multiple data categories according to the key business data; In the business data in the data category, the large language model is used to obtain the association relationship between entities, and the temporal relationship between the entities and the causal relationship between the entities are screened out according to the association relationship to obtain the business constraint conditions of the business data; An entity relationship model is established based on the association relationship between the entities, the entities in the entity relationship model are identified by the business constraints, and the entity relationship model is filled with the business data in the data category to obtain a data analysis model, and the current business data is input into the data analysis model to obtain an analysis result of the current business data.

2. The method for analyzing business data according to claim 1, characterized in that: The method of using the large language model to modify errors in the original business data and identify key business data in the original business data, and dividing the modified original business data into multiple data categories according to the key business data, includes: After modifying the errors in the original business data using the large language model, identifying key business data in the original business data in the modified original business data; The data format of the modified original business data is standardized to obtain standardized business data, and the standardized business data is divided into multiple data categories according to the key business data using the large speech model.

3. The method for analyzing business data according to claim 1, characterized in that: In the business data in the data category, the large language model is used to obtain the association relationship between entities, and the temporal relationship between the entities and the causal relationship between the entities are screened out according to the association relationship to obtain the business constraints of the business data, including: In the business data in the data category, the large language model is used to obtain the association relationship between entities; The large language model is used to screen out the temporal relationship between the entities and the causal relationship between the entities in the association relationship, and the temporal relationship between the entities and the causal relationship between the entities are analyzed to obtain the business constraints of the entities.

4. The method for analyzing business data according to claim 1, characterized in that: The method further comprises: Financial entities and relationships between financial entities are extracted from a database of financial business data, a financial domain ontology library is constructed, and the large language model is obtained by training using the financial domain ontology library.

5. The method for analyzing business data according to claim 1, characterized in that: The step of establishing an entity relationship model based on the association relationship between the entities, identifying entities in the entity relationship model with the business constraint conditions, filling the entity relationship model with the business data in the data category to obtain a data analysis model, and inputting current business data into the data analysis model to obtain an analysis result of the current business data includes: Establishing an entity relationship model according to the association relationship between the entities, and identifying the entities in the entity relationship model with the business constraint conditions; Analyze business data according to the data category to obtain regional business data and product business data, fill the entity relationship model with the regional business data and the product business data to obtain a data analysis model, and input current business data into the data analysis model to obtain the analysis result of the current business data.

6. The method for analyzing business data according to claim 1 or 5, characterized in that: The step of inputting the current business data into the data analysis model to obtain the analysis result of the current business data includes: The current business data includes current customer data and / or current product data. The current business data is input into the data analysis model to obtain the analysis results of the current business data. The analysis results of the current business data include current customer risk analysis results and / or current product business indicator analysis results.

7. The method for analyzing business data according to claim 1, characterized in that: After filling the entity relationship model according to the business data in the data category to obtain the data analysis model, the method further includes: The data analysis model is updated by one or more of updating entities, updating attribute fields of business data, and updating business constraints.

8. A device for analyzing business data, characterized in that: include: A processing module, used to modify errors in the original business data and identify key business data in the original business data using a large language model, and divide the modified original business data into multiple data categories according to the key business data; A conditional module, used to obtain the association relationship between entities in the business data in the data category using the large language model, and screen out the temporal relationship between the entities and the causal relationship between the entities according to the association relationship, so as to obtain the business constraint conditions of the business data; An analysis module is used to establish an entity relationship model based on the association relationship between the entities, identify the entities in the entity relationship model with the business constraints, fill the entity relationship model with the business data in the data category to obtain a data analysis model, and input the current business data into the data analysis model to obtain the analysis results of the current business data.

9. An electronic device for analyzing business data, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images