Financial data difference identification method and device, equipment and storage medium

Abstract

The invention discloses a financial data difference identification method and device, equipment and a storage medium, and belongs to the technical field of big data. The difference between business data and financial vouchers is automatically identified through a business difference platform, and the platform integrates a business data clustering model, an accounting basic rule base, a financial voucher template base and a difference identification model. Firstly, to-be-processed business data are imported, and the data are grouped by using a clustering model; and then, matching suitable accounting rules and voucher templates in the rule library and the template library respectively to generate accounting vouchers after data grouping. And finally, obtaining an original accounting document corresponding to the business data, and comparing the difference between the two through a difference identification model. The invention further relates to the technical field of the block chain, and the business data is stored on the block chain node. The business data is processed based on the clustering model of the business difference platform, and the voucher difference is accurately identified by using the difference identification model, so that the accuracy and efficiency of financial data difference identification are improved.

Description

Technical Field

[0001] The present application belongs to the field of big data technology, and specifically relates to a method, device, computer equipment and storage medium for identifying differences in financial data. Background Art

[0002] As people's insurance awareness continues to improve, the scope of insurance business is becoming wider and wider. The operation of insurance companies is increasingly dependent on the reliability of information systems, among which the reliability of financial systems is particularly important.

[0003] Although many insurance companies have realized the automatic generation of business data to accounting vouchers, there is a lack of good monitoring methods for how to quickly discover the differences between business and finance. At present, the verification of business and financial differences is mostly in the form of manual verification, which brings a lot of workload and confusion to financial staff. For example, the actual write-off of some accounts is recorded in the ledger, the correctness of the key segment values ​​of the voucher is verified through temporary data collection, and the consistency between the amount of the accounting voucher and the amount of the business. These verification operations require financial personnel to spend a lot of time and energy to complete. The checkpoints involved in the entire verification process are scattered and difficult to standardize, and there are many blind spots left. It is easy to make omissions or mistakes through manual verification, which may lead to financial risks or regulatory risks for the company in serious cases.

[0004] Therefore, although the financial system automatically generates accounting vouchers, which is fast and convenient, how to quickly discover the differences between business and finance and to check for business anomalies through the differences between business and finance is an urgent task that all insurance companies need to solve. Summary of the invention

[0005] The purpose of the embodiments of the present application is to propose a method, device, computer equipment and storage medium for identifying financial data differences, so as to solve the problems existing in the existing business-finance difference monitoring methods, which require financial personnel to spend more time and energy, and are prone to omissions or mistakes.

[0006] In order to solve the above technical problems, the present application embodiment provides a method for identifying differences in financial data, which adopts the following technical solution:

[0007] A financial data difference identification method is applied to a business difference platform. The business difference platform includes a business data model, an accounting basic rule library, a financial voucher template library and a difference identification model. The business data model is a clustering model. The data difference identification method includes:

[0008] Obtain the business data to be processed and import it into the business difference platform;

[0009] Use the business data model to perform clustering operations on the business data to be processed to obtain a business data subset;

[0010] Search the accounting basic rules matching the business data subset in the accounting basic rule library to obtain the target accounting basic rules;

[0011] Search the financial voucher template library for a financial voucher template that matches the business data subset, and obtain the target financial voucher template;

[0012] Generate an accounting voucher for the business data subset based on the target accounting basic rules and the target financial voucher template to obtain a first accounting voucher;

[0013] The original accounting voucher of the business data to be processed is obtained to obtain a second accounting voucher, and the difference between the first accounting voucher and the second accounting voucher is identified using a difference identification model to obtain a data difference result.

[0014] Furthermore, the step of using the business data model to perform clustering operations on the business data to be processed to obtain a business data subset specifically includes:

[0015] Identify the business types of the business data to be processed and count the number of business types;

[0016] Set a matching number of cluster centers based on the number of business types;

[0017] Cluster the business data to be processed based on the cluster center point and obtain the clustering result;

[0018] Based on the clustering results, the business data to be processed is divided into data to obtain business data subsets.

[0019] Furthermore, the step of clustering the service data to be processed based on the cluster center point and obtaining the clustering result specifically includes:

[0020] Constructing a cluster space coordinate system based on the cluster center point, and obtaining the coordinate value of the cluster center point in the cluster space coordinate system to obtain a first coordinate;

[0021] Mapping the service data to be processed into the cluster space coordinate system, and obtaining the coordinate value of the service data to be processed in the cluster space coordinate system to obtain a second coordinate;

[0022] Calculate the distance between the first coordinate and the second coordinate to obtain several clustering distances;

[0023] Cluster the business data to be processed according to several clustering distances to obtain clustering results.

[0024] Furthermore, the steps of clustering the service data to be processed according to a plurality of clustering distances and obtaining clustering results specifically include:

[0025] Sort several cluster distances to obtain distance sorting results;

[0026] Determine the minimum clustering distance based on the distance sorting results;

[0027] Determine the target cluster center matching the business data to be processed based on the minimum cluster distance;

[0028] Allocate the business data to be processed to the target cluster center to obtain the clustering result.

[0029] Furthermore, the step of dividing the service data to be processed based on the clustering result to obtain a service data subset specifically includes:

[0030] Determine the distribution of pending business data near each cluster center based on the clustering results;

[0031] Determine the data-dense areas of each cluster center based on the distribution of the business data to be processed;

[0032] The business data to be processed in each data-dense area is obtained in turn to obtain a business data subset.

[0033] Furthermore, the difference identification model is a decision tree model, and the step of using the difference identification model to identify the difference between the first accounting document and the second accounting document to obtain the data difference result specifically includes:

[0034] Acquire text data in a first accounting voucher to obtain a first text, and perform entity recognition and relationship extraction on the first text to obtain a first text entity and a first entity relationship;

[0035] Acquire text data in a second accounting voucher to obtain a second text, and perform entity recognition and relationship extraction on the second text to obtain a second text entity and a second entity relationship;

[0036] Importing the first text entity and the first entity relationship into the difference recognition model to generate a first decision tree;

[0037] Importing the second text entity and the second entity relationship into the difference recognition model to generate a second decision tree;

[0038] Compare the first decision tree and the second decision tree to obtain data difference results.

[0039] Furthermore, the step of comparing the first decision tree and the second decision tree to obtain a data difference result specifically includes:

[0040] Acquire path data of the first decision tree to obtain first path data;

[0041] Acquire the path data of the second decision tree to obtain second path data;

[0042] Compare the first path data with the second path data to obtain a path difference result;

[0043] Determine the target first accounting document that has a difference with the second accounting document based on the path difference result;

[0044] Determine the business data subset corresponding to the target first accounting document and obtain the data difference result.

[0045] In order to solve the above technical problems, the embodiment of the present application further provides a financial data difference identification device, which adopts the following technical solution:

[0046] A financial data difference identification device, the data difference identification device is used to run a business difference platform, the business difference platform includes a business data model, an accounting basic rule library, a financial voucher template library and a difference identification model, the business data model is a clustering model, and the data difference identification device includes:

[0047] The data import module is used to obtain the business data to be processed and import the business data to be processed into the business difference platform;

[0048] A clustering operation module is used to perform clustering operation on the business data to be processed using the business data model to obtain a business data subset;

[0049] A rule matching module is used to search the accounting basic rules matching the business data subset in the accounting basic rule library to obtain the target accounting basic rules;

[0050] The template matching module is used to search the financial voucher template library for a financial voucher template that matches the business data subset, and obtain a target financial voucher template;

[0051] A voucher making module, used for generating an accounting voucher of a business data subset based on a target accounting basic rule and a target financial voucher template, and obtaining a first accounting voucher;

[0052] The difference identification module is used to obtain the original accounting voucher of the business data to be processed, obtain the second accounting voucher, and use the difference identification model to identify the difference between the first accounting voucher and the second accounting voucher to obtain the data difference result.

[0053] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0054] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of any one of the above-mentioned methods for identifying differences in financial data when executing the computer-readable instructions.

[0055] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0056] A computer-readable storage medium having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by a processor, implement the steps of any one of the above-mentioned methods for identifying differences in financial data.

[0057] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0058] The present application discloses a method, device, equipment and storage medium for identifying differences in financial data, and belongs to the field of big data technology. The differences between business data and financial vouchers are automatically identified through a business difference platform, and the platform integrates a business data clustering model, a basic accounting rule library, a financial voucher template library and a difference identification model. First, the business data to be processed is imported, and the data is grouped using a clustering model; then, appropriate accounting rules and voucher templates are matched in the rule library and the template library respectively to generate accounting vouchers after the data is grouped. Finally, the original accounting vouchers corresponding to the business data are obtained, and the differences between the two are compared through a difference identification model. The present application utilizes a business difference platform, analyzes business data through a clustering model, matches accounting rules and voucher templates to generate expected vouchers, and then compares them with the original vouchers to identify voucher differences. The business difference platform integrates data models, rule libraries, template libraries and identification models, automatically processes data, accurately locates financial differences, and improves the efficiency and accuracy of financial management. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0060] Figure 1 An exemplary system architecture diagram is shown in which the present application can be applied;

[0061] Figure 2 A flow chart showing an embodiment of a method for identifying differences in financial data according to the present application is shown;

[0062] Figure 3 A schematic diagram showing the structure of an embodiment of a financial data difference identification device according to the present application is shown;

[0063] Figure 4 A schematic structural diagram of an embodiment of a computer device according to the present application is shown. DETAILED DESCRIPTION

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0065] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0066] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0067] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0068] Users can use terminal devices 101, 102, 103 to interact with server 105 through network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0069] Terminal devices 101, 102, 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, desktop computers, etc.

[0070] Server 105 can be a server that provides various services, such as a background server that provides support for pages displayed on terminal devices 101, 102, and 103. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks (CDNs), and big data and artificial intelligence platforms.

[0071] It should be noted that the financial data difference identification method provided in the embodiment of the present application is generally executed by a server, and accordingly, the financial data difference identification device is generally set in the server.

[0072] It should be understood that Figure 1 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 the implementation requirements.

[0073] Continue to refer Figure 2 , shows a flow chart of an embodiment of the financial data difference identification method according to the present application. The present application embodiment can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0074] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0075] This embodiment discloses a financial data difference identification method, which is applied to a business difference platform. The business difference platform includes a business data model, an accounting basic rule library, a financial voucher template library, and a difference identification model. The business data model is a clustering model. The data difference identification method includes:

[0076] S201, obtaining the business data to be processed, and importing the business data to be processed into the business difference platform.

[0077] Specifically, first, the system collects the business data to be processed from various business sources or data warehouses. These data include transaction records, customer information, product details, and other types. Then, through the data interface or batch upload, these business data to be processed are imported into a specially designed business difference platform. The platform integrates data processing and analysis technology, and can automatically pre-process, clean and format the imported data.

[0078] The business data to be processed is imported into the business difference platform through the message component. The message component is used as a bridge for data circulation to achieve efficient import of the business data to be processed into the business difference platform. Through mechanisms such as message queues or real-time data streams, business data is encapsulated into message formats and transmitted to the business difference platform safely and orderly, ensuring the integrity and consistency of the data while improving the flexibility and scalability of data processing.

[0079] S202, using the business data model to perform clustering operation on the business data to be processed to obtain a business data subset.

[0080] Specifically, the business data model is a clustering model. The introduction of the business data model enables effective management and analysis of complex business data to be processed. First, according to business characteristics and needs, an accurate business data model is constructed based on the clustering model, which can fully reflect the inherent structure and correlation of the data. Subsequently, data mining techniques such as clustering algorithms are used to perform in-depth operations on the imported business data, clustering similar or related data items together to form multiple business data subsets. This process not only simplifies the complexity of data processing, but also makes subsequent difference analysis more focused and efficient, which helps to quickly identify and resolve inconsistencies in business data.

[0081] S203, searching the accounting basic rule library for the accounting basic rule that matches the business data subset to obtain the target accounting basic rule.

[0082] Specifically, the integrated accounting basic rule base enables accurate matching and rule application of business data subsets. As a core knowledge base, the accounting basic rule base stores a wealth of accounting standards, policy regulations and business processing logic. When processing business data subsets, the system automatically retrieves accounting basic rules that match the data characteristics in the rule base, and quickly locates the target accounting basic rules through matching algorithms, ensuring that subsequent data processing, difference analysis and financial report preparation are in compliance with established accounting standards and specifications.

[0083] The accounting basic rule library contains a variety of accounting basic rules to support complex accounting processes. For example, the accounting rule engine, as the core, is responsible for automatically triggering the corresponding accounting processing logic according to the business type; the accounting department basic rules specify in detail the specific requirements and processes that different departments must follow when recording accounts; the cost center basic rules clarify the principles and methods of cost allocation and aggregation to ensure the accuracy and rationality of cost calculation; and the sub-item basic rules specify the more granular sub-items under accounting subjects, such as expense types, expenditure items, etc., which provide a basis for refined financial management. These rules are interrelated and complementary, and together constitute a complete framework for corporate accounting processing.

[0084] When processing a subset of business data, the system first extracts key features of the data, such as business type, cost center code, accounting subject, etc. These features are then input into the matching algorithm, which traverses the accounting basic rule library and compares it with the accounting basic rules in the library according to the preset matching logic (such as keyword matching, rule expression matching, etc.), finds the accounting basic rule that fully matches or is closest to the data features, and marks the rule as the target accounting basic rule.

[0085] S204, searching the financial voucher template library for a financial voucher template that matches the business data subset to obtain a target financial voucher template.

[0086] Specifically, by integrating the financial voucher template library, the automatic mapping of business data subsets to financial voucher generation is achieved. When the business data subset is processed and ready for financial recording, the system searches for matching templates in the financial voucher template library. These templates are pre-designed according to financial standards and business needs, and contain the standard format, field requirements and filling logic of financial vouchers. Through the matching algorithm, the system can quickly locate the financial voucher template that is suitable for the target business data subset, and then guide the subsequent voucher generation process, which not only improves the accuracy and standardization of financial vouchers, but also significantly improves the efficiency and consistency of financial processing.

[0087] S205, generating an accounting voucher for the business data subset based on the target accounting basic rules and the target financial voucher template to obtain a first accounting voucher.

[0088] Specifically, by combining the target accounting basic rules with the target financial voucher template, efficient accounting voucher generation for the business data subset is achieved. After determining the accounting basic rules and financial voucher templates that match the business data subset, the system automatically extracts key information from the business data, such as transaction amount, accounting subject, summary, etc., according to the accounting processing logic defined in the rules and the voucher format preset in the template, and fills it into the corresponding position of the template. Subsequently, the system verifies the generated voucher to ensure that it complies with accounting standards and internal regulations. Finally, the accounting voucher for the business data subset is generated, that is, the first accounting voucher.

[0089] S206, obtaining the original accounting voucher of the business data to be processed, obtaining a second accounting voucher, and using a difference identification model to identify the difference between the first accounting voucher and the second accounting voucher to obtain a data difference result.

[0090] Specifically, the difference recognition model is used to analyze and compare changes in business data in financial records. First, the system obtains the original accounting voucher of the business data to be processed from the data source, that is, the second accounting voucher, which records the initial financial information of the business. Subsequently, the first accounting voucher previously generated based on the business data subset is used to import the two into the difference recognition model for comparison. The difference recognition model analyzes the various data in the accounting voucher, including but not limited to the amount, subject, summary, etc., to quickly identify the differences between the two. Finally, detailed data difference results are output to provide clear financial change information for corporate financial managers for subsequent business verification, adjustment or audit.

[0091] The decision tree model is used as the difference recognition model. For the text data of the first and second accounting documents, the natural language processing technology is first used to perform entity recognition and relationship extraction, and the entities and their relationships of the two sets of texts are constructed respectively. Subsequently, the two sets of entities and relationships are used as inputs and imported into the decision tree model respectively to construct the corresponding decision tree structure, forming the first decision tree and the second decision tree. Finally, by comparing the structure and node information of the two decision trees, the difference points between the two decision trees are automatically identified and extracted, that is, the data difference results.

[0092] In the above embodiment, the present application discloses a method for identifying differences in financial data, which belongs to the field of big data technology. The differences between business data and financial vouchers are automatically identified through a business difference platform, and the platform integrates a business data clustering model, an accounting basic rule library, a financial voucher template library, and a difference identification model. First, the business data to be processed is imported, and the data is grouped using a clustering model; then, appropriate accounting rules and voucher templates are matched in the rule library and the template library respectively to generate accounting vouchers after the data is grouped. Finally, the original accounting vouchers corresponding to the business data are obtained, and the differences between the two are compared through a difference identification model. The present application utilizes a business difference platform, analyzes business data through a clustering model, matches accounting rules and voucher templates to generate expected vouchers, and then compares them with the original vouchers to identify voucher differences. The business difference platform integrates data models, rule libraries, template libraries, and identification models to automatically process data, accurately locate financial differences, and improve financial management efficiency and accuracy.

[0093] Furthermore, the step of using the business data model to perform clustering operations on the business data to be processed to obtain a business data subset specifically includes:

[0094] Identify the business types of the business data to be processed and count the number of business types;

[0095] Set a matching number of cluster centers based on the number of business types;

[0096] Cluster the business data to be processed based on the cluster center point and obtain the clustering result;

[0097] Based on the clustering results, the business data to be processed is divided into data to obtain business data subsets.

[0098] In this embodiment, the business data model is a clustering model, which divides the business data into different subsets according to similarity, which helps to more accurately identify the characteristics and patterns of the business data. In the clustering operation process, the business type of the business data to be processed is first accurately identified, such as sales business, procurement business, inventory business, accounts receivable and payable business, production cost business, etc. Then, the matching number of cluster center points is set according to the number of business types. For example, when the number of business types is 5, 5 cluster center points are set. Then, these cluster center points are used to cluster the business data to be processed, and the generated clustering results are 5 cluster center areas or 5 cluster clusters. Finally, the data is divided based on the clustering results to form business data subsets.

[0099] In the above embodiment, by identifying business types, counting their numbers, and setting cluster centers accordingly, these centers are used to perform clustering operations on business data to form clustering results. Finally, the data is divided based on the clustering results to obtain business data subsets, thereby realizing intelligent classification of business data.

[0100] Furthermore, the step of clustering the service data to be processed based on the cluster center point and obtaining the clustering result specifically includes:

[0101] Constructing a cluster space coordinate system based on the cluster center point, and obtaining the coordinate value of the cluster center point in the cluster space coordinate system to obtain a first coordinate;

[0102] Mapping the service data to be processed into the cluster space coordinate system, and obtaining the coordinate value of the service data to be processed in the cluster space coordinate system to obtain a second coordinate;

[0103] Calculate the distance between the first coordinate and the second coordinate to obtain several clustering distances;

[0104] Cluster the business data to be processed according to several clustering distances to obtain clustering results.

[0105] In this embodiment, firstly, by defining the cluster center points and constructing a multidimensional cluster space coordinate system, the spatial position of each center point (i.e., the first coordinate) is accurately obtained to realize the construction of the clustering framework. Subsequently, the business data to be processed is mapped to the coordinate system constructed above using data mapping technology, and the precise position of each data point in the coordinate system (i.e., the second coordinate) is calculated. Then, a distance measurement algorithm (such as Euclidean distance, Manhattan distance, etc.) is used to calculate the distance between the first coordinate and the second coordinate of each data point to each cluster center to obtain a cluster distance set. Finally, based on these cluster distances, a clustering algorithm is used to distribute the business data to be processed to the closest cluster center according to the principle of distance similarity, thereby completing the clustering process and outputting the clustering results.

[0106] In the above embodiment, a spatial coordinate system is constructed by cluster center points, the business data is mapped to the coordinate system, the distance between the cluster center points and the data points is calculated, the business data is clustered according to the calculated distance, and the clustering results are output, thereby achieving accurate business data clustering analysis.

[0107] Furthermore, the steps of clustering the service data to be processed according to a plurality of clustering distances and obtaining clustering results specifically include:

[0108] Sort several cluster distances to obtain distance sorting results;

[0109] Determine the minimum clustering distance based on the distance sorting results;

[0110] Determine the target cluster center matching the business data to be processed based on the minimum cluster distance;

[0111] Allocate the business data to be processed to the target cluster center to obtain the clustering result.

[0112] In this embodiment, in the subsequent stage of cluster analysis, a sorting algorithm (such as quick sort, merge sort, etc.) is first used to sort the calculated cluster distances to obtain a distance sorting result. Then, by traversing the sorting results or directly using the characteristics of the sorting algorithm, the minimum cluster distance is quickly located, and the minimum cluster distance reflects the highest similarity or nearest neighbor relationship between the service data to be processed and a certain cluster center.

[0113] Based on the minimum clustering distance, the nearest neighbor principle or similarity matching mechanism is used to accurately determine the target cluster center that best matches the business data to be processed. Finally, the clustering allocation operation is performed to classify the business data to be processed into the determined target cluster center, and the final clustering result is obtained and output.

[0114] In the above embodiment, by sorting the clustering distances, accurately identifying the minimum distance, and quickly matching the business data to the optimal clustering center, not only the clustering efficiency is improved, but also the accuracy of the clustering results is ensured, so that the business data can be efficiently classified.

[0115] Furthermore, the step of dividing the service data to be processed based on the clustering result to obtain a service data subset specifically includes:

[0116] Determine the distribution of pending business data near each cluster center based on the clustering results;

[0117] Determine the data-dense areas of each cluster center based on the distribution of the business data to be processed;

[0118] The business data to be processed in each data-dense area is obtained in turn to obtain a business data subset.

[0119] In this embodiment, based on the cluster analysis, the division of business data is further refined. First, by analyzing the clustering results, the distribution of the business data to be processed around each cluster center is clarified, and the areas where the data points are relatively concentrated are identified. Then, focus on the areas where these data points are relatively concentrated, and determine the data dense areas, that is, the parts where the business data is highly concentrated and has similar characteristics. Then, an iterative or batch processing method is used to extract and integrate the business data to be processed from each data dense area one by one, and finally form multiple business data subsets with clear business characteristics and high cohesion.

[0120] In the above embodiment, business data is accurately divided through clustering results, data-dense areas are determined, and business data subsets are effectively extracted, thereby improving the precision of data management and enhancing the flexibility and efficiency of data processing and application.

[0121] Furthermore, the difference identification model is a decision tree model, and the step of using the difference identification model to identify the difference between the first accounting document and the second accounting document to obtain the data difference result specifically includes:

[0122] Acquire text data in a first accounting voucher to obtain a first text, and perform entity recognition and relationship extraction on the first text to obtain a first text entity and a first entity relationship;

[0123] Acquire text data in a second accounting voucher to obtain a second text, and perform entity recognition and relationship extraction on the second text to obtain a second text entity and a second entity relationship;

[0124] Importing the first text entity and the first entity relationship into the difference recognition model to generate a first decision tree;

[0125] Importing the second text entity and the second entity relationship into the difference recognition model to generate a second decision tree;

[0126] Compare the first decision tree and the second decision tree to obtain data difference results.

[0127] In this embodiment, a decision tree model is used as a difference recognition model. For the text data of the first and second accounting documents, entity recognition and relationship extraction are first performed through natural language processing technology to respectively construct the entities of the two groups of texts and their mutual relationships. Subsequently, the two groups of entities and relationships are respectively imported into the decision tree model as input to construct corresponding decision tree structures to form the first decision tree and the second decision tree. Finally, by comparing the structure and node information of the two decision trees, the difference points between the two decision trees, i.e., the data difference results, are automatically identified and extracted.

[0128] The decision tree is used to identify the differences in accounting documents because it is intuitive, easy to understand and explain, and can directly show the key factors and paths in the identification process. In addition, the decision tree model can automatically learn and build classification rules from a large amount of accounting document data, effectively dealing with complex and changeable financial data, and its classification accuracy is high, which can accurately capture the subtle differences between accounting documents and improve the accuracy of identification. At the same time, the output results of the decision tree model are clear, which makes it easy for auditors and financial personnel to quickly understand the reasons for the differences and make corresponding decisions and processing.

[0129] In the above embodiment, the decision tree model is used to effectively identify the subtle differences between accounting documents, and accurate comparison of financial data is achieved. By extracting text entities and relationships, a unique decision tree structure is constructed, and then the decision tree differences are compared to quickly identify data change points, thereby improving the accuracy and efficiency of difference identification.

[0130] Furthermore, the step of comparing the first decision tree and the second decision tree to obtain a data difference result specifically includes:

[0131] Acquire path data of the first decision tree to obtain first path data;

[0132] Acquire the path data of the second decision tree to obtain second path data;

[0133] Compare the first path data with the second path data to obtain a path difference result;

[0134] Determine the target first accounting document that has a difference with the second accounting document based on the path difference result;

[0135] Determine the business data subset corresponding to the target first accounting document and obtain the data difference result.

[0136] In this embodiment, when identifying the difference between the first and second decision trees, the path data of the two are first extracted as the basis for comparison. The path data includes all decision conditions (such as entity attributes, relationship types, etc.) from the root node to the leaf node and their order. By carefully comparing the first path data with the second path data, the difference between the two is accurately identified, that is, the path difference result. Subsequently, based on these path difference results, the first accounting voucher that is inconsistent with the second accounting voucher is quickly located, that is, the target first accounting voucher. Finally, the business data subset associated with the target accounting voucher is determined and output as the final data difference result.

[0137] Suppose there are two accounting documents about company purchases. The first one records a successful purchase of office supplies, and the second one records the purchase plan adjusted due to a change in supplier. When using the decision tree model for difference identification, the path data of each of the two accounting documents will be extracted first.

[0138] In the decision tree of the first accounting document, the path data includes the path starting from the "purchase application" node, passing through the "office supplies category" (entity attribute), "purchase quantity" (entity attribute), "supplier A" (entity relationship), "contract signing" (decision condition) and other nodes, and finally reaching the "purchase completed" (leaf node). The decision tree path of the second accounting document changes at the "supplier" node to "supplier B", and triggers subsequent nodes such as "price renegotiation" (new decision condition) and "contract revision" (new decision condition), and finally reaches "purchase completed", but the paths of the two are different.

[0139] By comparing the data of these two paths, we can identify the differences between the two, namely, the change of supplier from A to B, and the series of subsequent operational differences caused by this, such as price negotiation and contract revision. These differences are the path difference results, which directly reflect the differences between the two procurement activities.

[0140] Taking corporate procurement as an example, suppose the second accounting voucher records the changes in a certain purchase, such as a supplier change. By comparing the path differences between the first decision tree (original procurement plan) and the second decision tree, it is found that the path after the "supplier" node has changed significantly. Based on these differences, the system quickly locates the target first accounting voucher that is inconsistent with the changed second accounting voucher, that is, the accounting voucher of the original procurement plan. Subsequently, the business data subset associated with the target accounting voucher is determined, such as the original supplier information, the original price terms, etc. These data information constitute the data difference results compared with the changed procurement situation.

[0141] In the above embodiment, by comparing the path data of the two decision trees, the differences between the accounting documents are quickly identified and accurately located to the specific business data subset, which not only improves the efficiency and accuracy of difference identification, but also facilitates the subsequent business analysis, data correction and financial auditing of the differences, effectively ensuring the integrity and accuracy of the company's accounting information.

[0142] In this embodiment, the electronic device (eg Figure 1 The server shown in the figure) can receive instructions or obtain data through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0143] It should be emphasized that in order to further ensure the privacy and security of the above business data, the above business data can also be stored in a blockchain node.

[0144] The blockchain referred to in this application is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm, etc. Blockchain is essentially a decentralized database, a string of data blocks generated by cryptographic methods. Each data block contains a batch of network transaction information, which is used to verify the validity of its information (anti-counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, platform product service layer, and application service layer.

[0145] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0146] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0147] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a financial data difference identification device, and the device embodiment is similar to Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0148] like Figure 3 As shown, the financial data difference identification device 300 described in this embodiment is used to run a business difference platform, which includes a business data model, an accounting basic rule library, a financial voucher template library and a difference identification model. The business data model is a clustering model. The data difference identification device 300 includes:

[0149] The data import module 301 is used to obtain the business data to be processed and import the business data to be processed into the business difference platform;

[0150] A clustering operation module 302 is used to perform clustering operation on the service data to be processed using the service data model to obtain a service data subset;

[0151] A rule matching module 303 is used to search the accounting basic rule library for the accounting basic rule that matches the business data subset, and obtain the target accounting basic rule;

[0152] The template matching module 304 is used to search the financial voucher template library for a financial voucher template that matches the business data subset, and obtain a target financial voucher template;

[0153] The voucher making module 305 is used to generate an accounting voucher of the business data subset based on the target accounting basic rules and the target financial voucher template to obtain a first accounting voucher;

[0154] The difference identification module 306 is used to obtain the original accounting voucher of the business data to be processed, obtain the second accounting voucher, and use the difference identification model to identify the difference between the first accounting voucher and the second accounting voucher to obtain a data difference result.

[0155] Furthermore, the clustering operation module 302 is used to:

[0156] Identify the business types of the business data to be processed and count the number of business types; set a matching number of cluster centers based on the number of business types; cluster the business data to be processed based on the cluster centers to obtain clustering results; divide the business data to be processed based on the clustering results to obtain business data subsets.

[0157] Furthermore, the clustering operation module 302 is specifically used for:

[0158] A cluster space coordinate system is constructed based on the cluster center point, and the coordinate value of the cluster center point in the cluster space coordinate system is obtained to obtain the first coordinate; the business data to be processed is mapped to the cluster space coordinate system, and the coordinate value of the business data to be processed in the cluster space coordinate system is obtained to obtain the second coordinate; the distance between the first coordinate and the second coordinate is calculated to obtain several cluster distances; the business data to be processed is clustered according to the several cluster distances to obtain the clustering results.

[0159] Furthermore, the clustering operation module 302 is further used to:

[0160] Sort several cluster distances to obtain a distance sorting result; determine the minimum cluster distance based on the distance sorting result; determine a target cluster center that matches the business data to be processed based on the minimum cluster distance; assign the business data to be processed to the target cluster center to obtain a clustering result.

[0161] Furthermore, the clustering operation module 302 is also used for:

[0162] Based on the clustering results, the distribution of pending business data near each cluster center is determined; based on the distribution of pending business data, the data dense area of ​​each cluster center is determined; the pending business data in each data dense area is acquired in turn to obtain a business data subset.

[0163] Furthermore, the difference identification module 306 is used to:

[0164] Acquire text data in a first accounting voucher to obtain a first text, and perform entity recognition and relationship extraction on the first text to obtain a first text entity and a first entity relationship; acquire text data in a second accounting voucher to obtain a second text, and perform entity recognition and relationship extraction on the second text to obtain a second text entity and a second entity relationship; import the first text entity and the first entity relationship into a difference recognition model to generate a first decision tree; import the second text entity and the second entity relationship into a difference recognition model to generate a second decision tree; compare the first decision tree and the second decision tree to obtain a data difference result.

[0165] Furthermore, the difference identification module 306 is further used to:

[0166] Obtain path data of the first decision tree to obtain first path data; obtain path data of the second decision tree to obtain second path data; compare the first path data with the second path data to obtain a path difference result; determine a target first accounting voucher that differs from the second accounting voucher based on the path difference result; determine a business data subset corresponding to the target first accounting voucher to obtain a data difference result.

[0167] In the above embodiment, the present application discloses a financial data difference identification device, which belongs to the field of big data technology. The differences between business data and financial vouchers are automatically identified through a business difference platform, and the platform integrates a business data clustering model, an accounting basic rule library, a financial voucher template library and a difference identification model. First, the business data to be processed is imported, and the data is grouped using a clustering model; then, appropriate accounting rules and voucher templates are matched in the rule library and the template library respectively to generate accounting vouchers after the data is grouped. Finally, the original accounting vouchers corresponding to the business data are obtained, and the differences between the two are compared through a difference identification model. The present application utilizes a business difference platform, analyzes business data through a clustering model, matches accounting rules and voucher templates to generate expected vouchers, and then compares them with the original vouchers to identify voucher differences. The business difference platform integrates data models, rule libraries, template libraries and identification models, automatically processes data, accurately locates financial differences, and improves financial management efficiency and accuracy.

[0168] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0169] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmab l eGate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0170] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0171] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk equipped on the computer device 4, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the financial data difference identification method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.

[0172] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions stored in the memory 41 or process data, such as computer-readable instructions for running the financial data difference identification method.

[0173] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.

[0174] In the above embodiment, the present application discloses a computer device, which belongs to the field of big data technology. The differences between business data and financial vouchers are automatically identified through a business difference platform, and the platform integrates a business data clustering model, an accounting basic rule library, a financial voucher template library, and a difference identification model. First, the business data to be processed is imported, and the data is grouped using a clustering model; then, appropriate accounting rules and voucher templates are matched in the rule library and the template library respectively to generate accounting vouchers after the data is grouped. Finally, the original accounting vouchers corresponding to the business data are obtained, and the differences between the two are compared through a difference identification model. The present application utilizes a business difference platform, analyzes business data through a clustering model, matches accounting rules and voucher templates to generate expected vouchers, and then compares them with the original vouchers to identify voucher differences. The business difference platform integrates data models, rule libraries, template libraries, and identification models to automatically process data, accurately locate financial differences, and improve financial management efficiency and accuracy.

[0175] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the financial data difference identification method as described above.

[0176] In the above embodiment, the present application discloses a computer-readable storage medium, which belongs to the field of big data technology. The differences between business data and financial vouchers are automatically identified through a business difference platform, and the platform integrates a business data clustering model, an accounting basic rule library, a financial voucher template library, and a difference identification model. First, the business data to be processed is imported, and the data is grouped using a clustering model; then, appropriate accounting rules and voucher templates are matched in the rule library and the template library respectively to generate accounting vouchers after data grouping. Finally, the original accounting vouchers corresponding to the business data are obtained, and the differences between the two are compared through a difference identification model. The present application utilizes a business difference platform, analyzes business data through a clustering model, matches accounting rules and voucher templates to generate expected vouchers, and then compares them with the original vouchers to identify voucher differences. The business difference platform integrates data models, rule libraries, template libraries, and identification models to automatically process data, accurately locate financial differences, and improve financial management efficiency and accuracy.

[0177] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0178] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0179] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for identifying differences in financial data, characterized in that: The data difference identification method is applied to a business difference platform, which includes a business data model, an accounting basic rule library, a financial voucher template library and a difference identification model. The business data model is a clustering model. The data difference identification method includes: Acquire the business data to be processed, and import the business data to be processed into the business difference platform; Using the business data model to perform clustering operations on the business data to be processed to obtain a business data subset; Searching the accounting basic rule library for an accounting basic rule that matches the business data subset to obtain a target accounting basic rule; Searching the financial voucher template library for a financial voucher template that matches the business data subset to obtain a target financial voucher template; Based on the target accounting basic rules and the target financial voucher template, generate an accounting voucher for the business data subset to obtain a first accounting voucher; The original accounting voucher of the business data to be processed is obtained to obtain a second accounting voucher, and the difference between the first accounting voucher and the second accounting voucher is identified using the difference identification model to obtain a data difference result.

2. The method for identifying financial data differences according to claim 1, characterized in that: The step of using the business data model to perform clustering operations on the business data to be processed to obtain a business data subset specifically includes: Identifying the business type of the business data to be processed, and counting the number of the business type; Setting a matching number of cluster centers based on the number of the business types; Clustering the service data to be processed based on the cluster center point to obtain a clustering result; The business data to be processed is divided into data based on the clustering result to obtain the business data subset.

3. The method for identifying financial data differences according to claim 2, characterized in that: The step of clustering the service data to be processed based on the cluster center point to obtain a clustering result specifically includes: Constructing a cluster space coordinate system based on the cluster center point, and obtaining the coordinate value of the cluster center point in the cluster space coordinate system to obtain a first coordinate; Mapping the service data to be processed into the cluster space coordinate system, and obtaining the coordinate value of the service data to be processed in the cluster space coordinate system to obtain a second coordinate; Calculating the distance between the first coordinate and the second coordinate to obtain a plurality of clustering distances; The service data to be processed is clustered according to a plurality of clustering distances to obtain the clustering result.

4. The method for identifying financial data differences according to claim 3, characterized in that: The step of clustering the service data to be processed according to a plurality of clustering distances to obtain the clustering result specifically includes: Sorting a number of the cluster distances to obtain a distance sorting result; Determine a minimum clustering distance based on the distance sorting result; Determining a target cluster center matching the service data to be processed based on the minimum cluster distance; The service data to be processed is distributed to the target cluster center to obtain the clustering result.

5. The method for identifying financial data differences according to claim 2, characterized in that: The step of dividing the service data to be processed based on the clustering result to obtain the service data subset specifically includes: Determining the distribution of the to-be-processed business data near each of the cluster centers based on the clustering results; Determine the data-dense area of ​​each of the cluster centers based on the distribution of the service data to be processed; The business data to be processed in each of the data dense areas is acquired in sequence to obtain the business data subset.

6. The method for identifying financial data differences according to claim 1, characterized in that: The difference identification model is a decision tree model, and the step of using the difference identification model to identify the difference between the first accounting document and the second accounting document to obtain a data difference result specifically includes: Acquire text data in the first accounting voucher to obtain a first text, and perform entity recognition and relationship extraction on the first text to obtain a first text entity and a first entity relationship; Acquire text data in the second accounting voucher to obtain a second text, and perform entity recognition and relationship extraction on the second text to obtain a second text entity and a second entity relationship; Importing the first text entity and the first entity relationship into the difference recognition model to generate a first decision tree; Importing the second text entity and the second entity relationship into the difference recognition model to generate a second decision tree; The first decision tree and the second decision tree are compared to obtain the data difference result.

7. The method for identifying financial data differences according to claim 6, characterized in that: The step of comparing the first decision tree and the second decision tree to obtain the data difference result specifically includes: Acquire the path data of the first decision tree to obtain first path data; Acquire the path data of the second decision tree to obtain second path data; Comparing the first path data with the second path data to obtain a path difference result; Determine a target first accounting document having a difference with the second accounting document based on the path difference result; Determine the business data subset corresponding to the target first accounting document and obtain the data difference result.

8. A financial data difference identification device, characterized in that: The data difference identification device is used to run a business difference platform, which includes a business data model, an accounting basic rule library, a financial voucher template library and a difference identification model. The business data model is a clustering model. The data difference identification device includes: A data import module, used to obtain the business data to be processed and import the business data to be processed into the business difference platform; A clustering operation module, used to perform a clustering operation on the service data to be processed using the service data model to obtain a service data subset; A rule matching module, used for searching the accounting basic rule library for an accounting basic rule that matches the business data subset, and obtaining a target accounting basic rule; A template matching module, used for searching the financial voucher template library for a financial voucher template that matches the business data subset, and obtaining a target financial voucher template; A voucher making module, used for generating an accounting voucher of a business data subset based on the target accounting basic rules and the target financial voucher template, to obtain a first accounting voucher; The difference identification module is used to obtain the original accounting voucher of the business data to be processed, obtain the second accounting voucher, and use the difference identification model to identify the difference between the first accounting voucher and the second accounting voucher to obtain a data difference result.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the financial data difference identification method according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the financial data difference identification method according to any one of claims 1 to 7.

Images