Financial data automatic filling method, device and equipment and storage medium

Abstract

The invention discloses a financial data automatic filling method and device, equipment and a storage medium, and belongs to the technical field of big data. The method comprises the following steps: determining a data source corresponding to original financial data by using a pre-trained data classification model; acquiring a data processing rule engine and a target data filling template matched with the data source; performing data cleaning on the original financial data based on a data cleaning rule; performing data analysis on the standardized data by using a data analysis rule; performing association relation extraction on the target data source field and the target filling field by using a data mapping rule, and performing data field mapping according to the field association relation; and according to a data field mapping result, filling the target data source field into the target data filling template to generate a financial data report. The invention further relates to the technical field of block chains, and financial data are stored on the block chain nodes. According to the method and the device, the applicability and the operation convenience of automatic filling and reporting of financial data in a multi-source data scene are improved.

Description

Technical Field

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

[0002] Financial data reporting refers to the process of collecting, sorting, entering and submitting various data related to financial markets and financial institutions in accordance with certain rules and requirements. These data cover a wide range of areas, mainly including digital information related to asset prices, market activities, economic indicators and trading activities. In the financial field, a large amount of data is generated, analyzed and traded to support key activities such as investment decisions, risk management, market forecasting and pricing of financial products.

[0003] At present, financial data reporting is mainly done manually, which relies on the professional knowledge and experience of statisticians to complete the reporting work by manually entering data. However, this method is time-consuming and laborious, and is inefficient for reporting tasks with large amounts of data. In addition, human factors may lead to data entry errors or omissions during the manual reporting process.

[0004] In response to the defects of the above-mentioned manual reporting method, the system automatic reporting method has gradually emerged in the market, using information technology means, such as automated scripts, data interfaces, etc., to achieve automatic data collection, processing and verification. However, when the system automatic reporting method is used for scenarios with diverse data sources, it is necessary to develop corresponding data processing modules for each data source, which has high development and maintenance costs and requires professional personnel to operate and maintain. 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 automatic reporting of financial data, so as to solve the problem that the existing system automatic reporting method needs to develop corresponding data processing modules for each data source when dealing with scenarios with diverse data sources, which has high development and maintenance costs and requires professional personnel to operate and maintain.

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

[0007] A method for automatically filling in financial data, comprising:

[0008] Obtain the original financial data, and use the pre-trained data classification model to determine the data source corresponding to the original financial data to obtain the target data source;

[0009] Obtaining a data processing rule engine and a target data reporting template that match the target data source, wherein the data processing rule engine includes data cleaning rules, data parsing rules, and data mapping rules;

[0010] Clean the original financial data based on data cleaning rules to obtain standardized data;

[0011] Use data parsing rules to parse the standardized data and extract the target data source fields;

[0012] Use data mapping rules to extract associations between target data source fields and target reporting fields in target data reporting templates, obtain field associations, and perform data field mapping based on the field associations;

[0013] According to the data field mapping results, fill in the target data source fields into the target data reporting template to generate a financial data report.

[0014] Furthermore, before the step of obtaining the original financial data and using the pre-trained data classification model to determine the data source corresponding to the original financial data and obtaining the target data source, the method further includes:

[0015] Acquire a pre-collected historical financial data set, wherein the historical financial data set includes financial historical data from a plurality of data sources and a data source label corresponding to each historical financial data;

[0016] Perform feature processing on historical financial data to obtain features of historical financial data;

[0017] Import historical financial data features and data source labels into a pre-built initial classification model, and obtain the data source classification prediction results output by the model, where the initial classification model is built based on the random forest algorithm;

[0018] The initial classification model is iteratively updated based on the data source classification prediction results to obtain a trained data classification model.

[0019] Furthermore, the steps of importing the historical financial data features and data source labels into the pre-built initial classification model and obtaining the data source classification prediction results output by the model specifically include:

[0020] Use historical financial data features as input variables of the model, and use data source labels as output variables of the model;

[0021] Randomly combine the features of historical financial data to obtain several feature matrices;

[0022] Associate a data source label with each feature matrix to generate an associated feature matrix;

[0023] Import each associated feature matrix into the decision tree of the initial classification model in turn, and calculate the node split purity value of each decision tree;

[0024] According to the node splitting purity value of each decision tree, the data source classification prediction result is determined and output.

[0025] Furthermore, before the step of obtaining a data processing rule engine and a target data reporting template that match the target data source, the method further includes:

[0026] Obtain data processing logic corresponding to financial historical data from several data sources, where the data processing logic includes data cleaning logic, data parsing logic, and data mapping logic;

[0027] Perform rule transformation on data cleaning logic, data parsing logic and data mapping logic respectively to obtain data cleaning rules, data parsing rules and data mapping rules;

[0028] Build data processing rule engines corresponding to each data source based on data cleaning rules, data parsing rules, and data mapping rules;

[0029] Obtain historical data reports corresponding to financial historical data from several data sources, and identify fixed fields and reporting fields in the historical data reports;

[0030] Based on the fixed fields and reporting fields in the historical data report, generate data reporting templates corresponding to each data source.

[0031] Further, the steps of extracting the association relationship between the target data source field and the target reporting field in the target data reporting template using the data mapping rule to obtain the field association relationship, and performing data field mapping according to the field association relationship specifically include:

[0032] Using data mapping rules to perform semantic recognition of the target data source field and the target reporting field respectively, to obtain the first field semantics and the second field semantics;

[0033] Matching the target data source field with the target reporting field according to the first field semantics and the second field semantics, and generating a field association relationship according to the field matching result;

[0034] Data field mapping between target data source fields and target reporting fields is performed based on field association relationships.

[0035] Furthermore, the data processing rule engine also includes a data conversion rule, which uses the data mapping rule to extract the association relationship between the target data source field and the target reporting field in the target data reporting template to obtain the field association relationship, and performs data field mapping according to the field association relationship, and further includes:

[0036] Identify the data format of the target reporting field to obtain a first target data format;

[0037] Identify the data format of the target data source field to obtain a second target data format;

[0038] determining whether the first target data format matches the second target data format;

[0039] When the first target data format does not match the second target data format, the data format of the target data source field is converted into the first target data format using a data conversion rule.

[0040] Furthermore, the data processing rule engine also includes data verification rules and data correction rules. After filling the target data source fields into the target data reporting template according to the data field mapping result and generating the financial data report, it also includes:

[0041] Use data validation rules to perform semantic recognition on target data source fields and fixed fields in financial data reports to obtain semantic recognition results;

[0042] Determine whether there are any anomalies in the data reporting of financial data reports based on the semantic recognition results;

[0043] When there are anomalies in the data reporting of financial data reports, the financial data reports are re-reported using data correction rules combined with semantic recognition results and data field mapping results.

[0044] In order to solve the above technical problems, the embodiment of the present application also provides a financial data automatic reporting device, which adopts the following technical solution:

[0045] A financial data automatic reporting device, comprising:

[0046] A data classification module is used to obtain raw financial data and use a pre-trained data classification model to determine the data source corresponding to the raw financial data to obtain a target data source;

[0047] A data preparation module is used to obtain a data processing rule engine and a target data reporting template that match the target data source, wherein the data processing rule engine includes data cleaning rules, data parsing rules, and data mapping rules;

[0048] The data cleaning module is used to clean the original financial data based on the data cleaning rules to obtain standardized data;

[0049] A data parsing module, used to parse the standardized data using data parsing rules and extract target data source fields;

[0050] The data mapping module is used to extract the association relationship between the target data source field and the target reporting field in the target data reporting template using the data mapping rules, obtain the field association relationship, and perform data field mapping according to the field association relationship;

[0051] The data reporting module is used to fill in the target data source fields into the target data reporting template according to the data field mapping results to generate a financial data report.

[0052] 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:

[0053] A computer device comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the method for automatically filling in financial data as described in any one of the above items are implemented.

[0054] 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:

[0055] 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 the method for automatically filling in financial data as described in any one of the above.

[0056] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0057] The present application discloses a method, device, equipment and storage medium for automatic reporting of financial data, which belongs to the field of big data technology. The present application realizes automatic identification of the data source of the original financial data by introducing a pre-trained data classification model, and then automatically selects a matching data processing rule engine and reporting template according to the target data source, and standardizes the original data through data cleaning, parsing and mapping rules to ensure that data from different data sources can be uniformly mapped to the target reporting field, realizes automatic extraction and reporting of the association relationship between fields, reduces the manual development and maintenance requirements for each data source, significantly reduces the development and maintenance costs, and at the same time improves the automation level and accuracy of data reporting, so that the applicability and ease of operation of the system in multi-source data scenarios have been significantly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] 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.

[0059] Figure 1 An exemplary system architecture diagram is shown in which the present application can be applied;

[0060] Figure 2 A flow chart showing an embodiment of a method for automatically reporting financial data according to the present application is shown;

[0061] Figure 3 A schematic diagram of the structure of an embodiment of a financial data automatic reporting device according to the present application is shown;

[0062] Figure 4 A schematic structural diagram of an embodiment of a computer device according to the present application is shown. DETAILED DESCRIPTION

[0063] 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.

[0064] 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.

[0065] 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.

[0066] like Figure 1 As shown, the system architecture 100 may include a terminal device 101, a network 102 and a server 103. The terminal device 101 may be a laptop 1011, a tablet computer 1012 or a mobile phone 1013. The network 102 is used to provide a medium for a communication link between the terminal device 101 and the server 103. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0067] The user can use the terminal device 101 to interact with the server 103 through the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0068] The terminal device 101 can be any electronic device with a display screen and supporting web browsing. In addition to a laptop computer 1011, a tablet computer 1012 or a mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV), a laptop computer, a desktop computer, etc.

[0069] The server 103 may be a server that provides various services, such as a background server that provides support for a web page displayed on the terminal device 101 .

[0070] It should be noted that the method for automatically filling in financial data provided in the embodiment of the present application is generally executed by a server / terminal device, and accordingly, the automatic filling in financial data device is generally arranged in the server / terminal device.

[0071] It should be understood that Figure 1 The numbers of terminal devices, networks and servers in the embodiment are merely illustrative. The above system may have any number of terminal devices, networks and servers according to implementation requirements.

[0072] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for automatically reporting financial data according to the present application. The method for automatically reporting financial data comprises the following steps:

[0073] S201, obtaining original financial data, and using a pre-trained data classification model to determine a data source corresponding to the original financial data, to obtain a target data source.

[0074] Specifically, first, the system receives raw financial data from different channels or platforms, including data information on financial markets such as stocks, bonds, and futures. The raw financial data has different formats when input and may contain data from different sources, so a data classification model is required for identification. By using a pre-trained data classification model, the system can quickly and accurately identify the source category of the data. The classification model is usually trained based on a large amount of annotated historical data, and can identify the data source category to which each piece of data belongs based on features, field names, or content patterns, such as "stock market data" or "fund information." Through the prediction of the classification model, the system can automatically determine the source of the data without manual intervention, and further obtain the corresponding target data source information.

[0075] For example, classification algorithms in machine learning, such as support vector machines (SVM) or random forests (RandomForest), can be used to classify data sources and identify different types of data sources (such as databases, APIs, files, etc.).

[0076] S202, obtaining a data processing rule engine and a target data reporting template that match the target data source, wherein the data processing rule engine includes data cleaning rules, data parsing rules, and data mapping rules.

[0077] Specifically, after identifying the data source, the system selects the appropriate processing rule engine and reporting template based on the data source category. Each data source may have corresponding data formats, field requirements and business logic, so the system predefines a set of processing rule engines that match various data sources, covering cleaning, parsing and mapping rules, and provides corresponding reporting templates for each data source. Data cleaning rules can be used to process noisy data, null values ​​and fields with incorrect formats; data parsing rules are used to extract key information from complex source data, such as parsing date and numeric fields in financial time series; data mapping rules are responsible for matching the fields of the source data with the fields of the reporting template. The reporting template specifies the format, field structure and data requirements of the final report, thereby ensuring that all types of data are filled in according to the expected format and content.

[0078] S203, performing data cleaning on the original financial data based on the data cleaning rules to obtain standardized data.

[0079] Specifically, the system uses data cleaning rules to improve the data quality of raw financial data to ensure that all fields meet the system processing requirements. Data cleaning includes multiple steps: the first is missing value filling. For missing information in key fields, the system will fill it through the mean, mode or interpolation method to ensure the integrity of the data; the second is outlier detection. For abnormal data that exceeds a reasonable range, such as extremely high prices or negative values, the system will use the set rules to remove or replace abnormal values; in addition, format normalization processing includes unifying date fields into a specific format (such as YYYY-MM-DD), as well as processing currency symbols, numerical precision, etc. Through data cleaning, the system can clean the raw data from different data sources into standardized data that meets the processing requirements, so as to facilitate data analysis and data mapping.

[0080] For example, using anomaly detection algorithms in machine learning, such as Isolation Forest or Local Outlier Factor, can automatically identify and filter out abnormal data to ensure data accuracy and consistency. Using cluster analysis or decision trees, data in different formats, such as date, time, currency, etc., can be automatically identified and converted to achieve data standardization.

[0081] S204, using data parsing rules to parse the standardized data and extract target data source fields.

[0082] Specifically, after data cleaning is completed, the system applies data parsing rules to extract the core fields of the target data source from the standardized data, so as to decompose the complex data into a set of fields suitable for the reporting template. Parsing rules are designed according to the different characteristics of the data source. For example, when parsing a stock data source, key indicators such as the opening price, closing price, and highest price will be extracted. When parsing a bond data source, the focus may be on fields such as the coupon rate and maturity date. Parsing methods include field decomposition, format conversion, and content recognition, such as extracting dates, numbers, or strings from text through regular expressions, string segmentation, and other methods. The result of the parsing is a structured data set that contains fields that meet the reporting requirements, ensuring that the system can extract useful information from various types of data.

[0083] For example, according to the type of data source, the corresponding parsing algorithm or library (such as JDBC, HTTP client, file parser, etc.) is used to automatically parse the data and extract the required information.

[0084] S205, extracting associations between target data source fields and target reporting fields in a target data reporting template using data mapping rules to obtain field associations, and performing data field mapping according to the field associations.

[0085] Specifically, after completing the data parsing, the system matches the target data source fields with the fields in the target reporting template according to the data mapping rules to generate a field association relationship. First, the system compares the parsed fields with the fields in the reporting template through name similarity, data type, and semantic matching techniques to find the best match. For example, the string matching algorithm can be used to determine whether the "transaction time" matches the "date" field in the template, or the NLP technology can be used to identify the potential association between the "customer name" and the "company name". Once the association relationship between the fields is established, the system will perform automatic mapping of the data fields based on this relationship, and fill the parsed source data field content into the corresponding field of the template. Through this step, the system can realize the automatic conversion of different data source fields and the accurate filling of the reporting template.

[0086] For example, by using relationship extraction algorithms in machine learning, such as rule-based methods or deep learning methods (such as BERT, GPT, etc.), a mapping relationship between data source fields and target reporting fields can be automatically established.

[0087] S206, according to the data field mapping result, fill in the target data source field into the target data reporting template to generate a financial data report.

[0088] Specifically, based on the results of data field mapping, the system automatically fills the target data source fields into the predefined target data reporting template to form a financial data report that meets the reporting requirements. The system uses the mapping relationship as the basis for template reporting to ensure that the source data fields can accurately correspond and be filled into the corresponding report fields. For example, the "Opening Price" field in the mapping relationship corresponds to the "Open Price" column in the template, and the "Opening Price" data will be directly filled into the "Open Price" position of the report. The system fills all parsed fields into the corresponding report positions according to this logic, and performs data verification according to the template requirements, such as format verification and value range checking, to ensure the integrity and compliance of the report content. Finally, the financial data report generated by the system can be directly used for further business applications or submissions without additional manual intervention, thereby realizing an efficient process of automatic data reporting.

[0089] In the above embodiment, the present application discloses a method for automatically reporting financial data, which belongs to the field of big data technology. The present application scheme aims to use machine learning technology to build an intelligent data processing and reporting platform, which can automatically identify, parse and convert data from different sources, realize automatic data collection, processing, reporting and verification, thereby reducing development and maintenance costs and reducing dependence on professionals.

[0090] This application introduces a pre-trained data classification model to automatically identify the data source of raw financial data, and then automatically selects a matching data processing rule engine and reporting template based on the target data source. The raw data is standardized through data cleaning, parsing and mapping rules to ensure that data from different data sources can be uniformly mapped to the target reporting field, thereby automatically extracting and reporting the association between fields, reducing the need for manual development and maintenance of each data source, significantly reducing development and maintenance costs, and at the same time improving the automation level and accuracy of data reporting, thereby significantly improving the applicability and ease of operation of the system in multi-source data scenarios.

[0091] Furthermore, before the step of obtaining the original financial data and using the pre-trained data classification model to determine the data source corresponding to the original financial data and obtaining the target data source, the method further includes:

[0092] Acquire a pre-collected historical financial data set, wherein the historical financial data set includes financial historical data from a plurality of data sources and a data source label corresponding to each historical financial data;

[0093] Perform feature processing on historical financial data to obtain features of historical financial data;

[0094] Import historical financial data features and data source labels into a pre-built initial classification model, and obtain the data source classification prediction results output by the model, where the initial classification model is built based on the random forest algorithm;

[0095] The initial classification model is iteratively updated based on the data source classification prediction results to obtain a trained data classification model.

[0096] In this embodiment, firstly, the collected historical financial data sets are obtained. These data sets come from multiple data sources and contain clear data source labels. The data source labels are used to mark the source information of each piece of historical financial data. Then, the data set is feature processed, that is, the key features that can characterize the characteristics of different data sources are extracted, such as time dimension, field type, data format, etc. These feature data and label data are input into the initial classification model for training. The model is built based on the random forest algorithm. The random forest algorithm uses a large number of decision trees to enhance the classification effect through random sampling of features and sub-sampling of data sets, thereby improving the ability to distinguish data sources. After the model is initially trained, the model is iteratively updated using the classification prediction results, that is, the model parameters are tuned and the features are screened according to the classification results, and the classification accuracy of the model is continuously improved, and finally a mature data classification model is obtained. This model can be used to quickly and accurately identify the source of new financial data and adapt to different data sources.

[0097] Through the above steps, the system uses the random forest classification model to achieve efficient data source identification, reduce manual participation, and further improve the accuracy of data classification and the generalization ability of the model through model iterative optimization.

[0098] Furthermore, the steps of importing the historical financial data features and data source labels into the pre-built initial classification model and obtaining the data source classification prediction results output by the model specifically include:

[0099] Use historical financial data features as input variables of the model, and use data source labels as output variables of the model;

[0100] Randomly combine the features of historical financial data to obtain several feature matrices;

[0101] Associate a data source label with each feature matrix to generate an associated feature matrix;

[0102] Import each associated feature matrix into the decision tree of the initial classification model in turn, and calculate the node split purity value of each decision tree;

[0103] According to the node splitting purity value of each decision tree, the data source classification prediction result is determined and output.

[0104] In this embodiment, the system first uses the historical financial data features as the input variables of the initial classification model, and uses the corresponding data source labels as the output variables of the initial classification model. Next, the historical data features are randomly combined to generate multiple sets of feature matrices, each of which represents a different feature subset, which is used to enhance the feature diversity and robustness of the model. The system associates these feature matrices with the corresponding data source labels to form an associated feature matrix, in which each associated feature matrix corresponds to a specific data source label. In each decision tree of the random forest, the system gradually imports each associated feature matrix, and judges the effectiveness of the current feature combination for data source classification based on the calculated node split purity value, that is, the purity of each type of data source label in the node. The higher the split purity value, the more significant the classification effect of the feature combination in the decision tree. Finally, the system combines the split purity of all decision trees, obtains the data source classification prediction results and outputs them weightedly to improve the accuracy of classification and the generalization ability of the model.

[0105] Through the above steps, the system effectively utilizes a variety of feature combinations in the model training process, fully improves the classification model's ability to discriminate data sources, and ensures the reliability and accuracy of classification prediction results.

[0106] Furthermore, before the step of obtaining a data processing rule engine and a target data reporting template that match the target data source, the method further includes:

[0107] Obtain data processing logic corresponding to financial historical data from several data sources, where the data processing logic includes data cleaning logic, data parsing logic, and data mapping logic;

[0108] Perform rule transformation on data cleaning logic, data parsing logic and data mapping logic respectively to obtain data cleaning rules, data parsing rules and data mapping rules;

[0109] Build data processing rule engines corresponding to each data source based on data cleaning rules, data parsing rules, and data mapping rules;

[0110] Obtain historical data reports corresponding to financial historical data from several data sources, and identify fixed fields and reporting fields in the historical data reports;

[0111] Based on the fixed fields and reporting fields in the historical data report, generate data reporting templates corresponding to each data source.

[0112] In this embodiment, the system first extracts the data processing logic corresponding to the financial historical data from multiple data sources, including data cleaning logic for cleaning data, data parsing logic for parsing key fields, and data mapping logic for mapping data fields to standard fields. Subsequently, the system converts these logics into rules one by one, standardizes the cleaning, parsing and mapping logics into a series of data processing rules, so as to build an automated data processing process. Based on these standardized rules, the system generates corresponding data processing rule engines for each data source, so that the data of each data source can follow its unique cleaning, parsing and mapping rules in the processing engine, thereby ensuring the integrity and consistency of the data. On this basis, the system identifies fixed fields and reporting fields from historical data reports. By analyzing the structure and content of reports from different data sources, the system further defines the unchanged fields in the report as fixed fields, and defines the fields that change with the data content as reporting fields. Based on this classification, the system automatically generates corresponding data reporting templates for each data source, thereby forming a set of universal reporting frameworks suitable for various types of financial data sources.

[0113] Through the above steps, the system realizes the automatic construction of data processing rules and report templates, standardizes the cleaning, parsing, mapping and reporting of various data sources, greatly reduces the workload of manual configuration and maintenance, and improves the system's adaptability and reporting efficiency.

[0114] Further, the steps of extracting the association relationship between the target data source field and the target reporting field in the target data reporting template using the data mapping rule to obtain the field association relationship, and performing data field mapping according to the field association relationship specifically include:

[0115] Using data mapping rules to perform semantic recognition of the target data source field and the target reporting field respectively, to obtain the first field semantics and the second field semantics;

[0116] Matching the target data source field with the target reporting field according to the first field semantics and the second field semantics, and generating a field association relationship according to the field matching result;

[0117] Data field mapping between target data source fields and target reporting fields is performed based on field association relationships.

[0118] In this embodiment, the system first applies the data mapping rules to identify the semantics of the target data source field and the target reporting field to obtain the specific meaning or purpose of each field. Through the natural language processing (NLP) algorithm and the semantic analysis model, the field name, field content or field context description is analyzed one by one, thereby generating the semantic description of each field, namely the first field semantics (the semantics of the target data source field) and the second field semantics (the semantics of the target reporting field). After that, the system matches the first field semantics and the second field semantics, and uses methods such as semantic similarity calculation, keyword matching or context relevance to determine whether the two fields correspond. The matching process will be verified in many aspects such as semantic consistency, numerical type and business requirements to ensure that the matching of the fields is accurate and in line with business logic. The system establishes a field association relationship based on the field matching results, and orderly pairs the target data source field and the target reporting field. Next, the system maps the source field content to the reporting field according to these associations, realizing the automatic conversion and filling of data between fields. This data field mapping ensures the accurate transfer of source data between multiple formats, so that it meets specific reporting requirements.

[0119] Through the above steps, the system achieves accurate matching and automatic mapping of target data source fields and reporting fields, greatly improving the accuracy and consistency of data reporting, reducing the workload of manual mapping and improving reporting efficiency.

[0120] Furthermore, the data processing rule engine also includes a data conversion rule, which uses the data mapping rule to extract the association relationship between the target data source field and the target reporting field in the target data reporting template to obtain the field association relationship, and performs data field mapping according to the field association relationship, and further includes:

[0121] Identify the data format of the target reporting field to obtain a first target data format;

[0122] Identify the data format of the target data source field to obtain a second target data format;

[0123] determining whether the first target data format matches the second target data format;

[0124] When the first target data format does not match the second target data format, the data format of the target data source field is converted into the first target data format using a data conversion rule.

[0125] In this embodiment, the system first identifies the data format of the target reporting field and obtains the first target data format, which includes the data type of the field (such as date, value, string, etc.), accuracy requirements, unit system, etc. Next, the system identifies the data format of the target data source field accordingly to obtain the actual data format of the field, that is, the second target data format, so that the system can determine whether the source data meets the format required for reporting. The system then compares the first target data format and the second target data format to check whether the two are consistent. If the two match, the source data can be used directly to complete the reporting; if they do not match, the system will convert the format of the source field according to the pre-configured data conversion rules.

[0126] Data conversion rules perform necessary conversion operations according to the requirements of the target format, such as converting the date format from "DD / MM / YYYY" to "YYYY-MM-DD", converting the currency unit from "US dollars" to "RMB", etc., or performing decimal precision processing on numeric fields. After this series of format conversions, the data in the target data source field can be consistent with the format requirements of the reporting template, thereby avoiding format conflicts during data reporting and ensuring the standardization and accuracy of reporting.

[0127] In addition, based on the mapping relationship, you can also use conversion algorithms in machine learning, such as linear regression, polynomial regression, etc. (for numerical data), or rule-based methods (for classification or text data) to automatically convert data formats and values ​​to meet reporting requirements.

[0128] Through the above steps, the system automatically realizes the adaptation and conversion between the data source fields and the reporting field formats, eliminates format incompatibility issues, improves the automation and accuracy of data reporting, and reduces the time for manual adjustments and the possibility of errors.

[0129] Furthermore, the data processing rule engine also includes data verification rules and data correction rules. After filling the target data source fields into the target data reporting template according to the data field mapping result and generating the financial data report, it also includes:

[0130] Use data validation rules to perform semantic recognition on target data source fields and fixed fields in financial data reports to obtain semantic recognition results;

[0131] Determine whether there are any anomalies in the data reporting of financial data reports based on the semantic recognition results;

[0132] When there are anomalies in the data reporting of financial data reports, the financial data reports are re-reported using data correction rules combined with semantic recognition results and data field mapping results.

[0133] In this embodiment, the system first applies the data verification rules to perform semantic recognition on the target data source fields and fixed fields in the financial data report, thereby obtaining the semantic recognition results of each field, and uses natural language processing (NLP) technology to perform semantic analysis on the field content to ensure that the reporting of the field meets the expected business meaning and context. For example, if a field represents "transaction date", the system will verify whether its content is a valid date format and logical range through semantic recognition. Through the semantic recognition of all fields, the system can obtain the verification results of whether each field in the entire report meets the expected semantics. Subsequently, the system determines whether there are abnormalities in the data reporting in the report based on these semantic recognition results. The abnormalities may include logical inconsistencies of values ​​(such as errors in the time sequence relationship), non-standard formats (such as date format or unit errors), etc. When the system detects an abnormality, it will perform an automated correction process according to the preset data correction rules. At this time, the data correction rules will combine the semantic recognition results and field mapping results to determine the correction method. For example, for date errors, the system can automatically find and correct them to the correct date format, or infer the correct unit based on the mapping results. After the correction is completed, the system regenerates the report data that meets the reporting requirements to ensure the accuracy and consistency of the report content.

[0134] Through the above steps, the system realizes intelligent anomaly detection and automatic correction of financial data reports, reduces the workload of manual inspection and correction, improves the accuracy of report filling and data quality, and further ensures the reliability of report output.

[0135] In the above embodiment, the present application discloses a method for automatically reporting financial data, which belongs to the field of big data technology. The present application realizes automatic identification of the data source of the original financial data by introducing a pre-trained data classification model, and then automatically selects a matching data processing rule engine and reporting template according to the target data source, and standardizes the original data through data cleaning, parsing and mapping rules to ensure that data from different data sources can be uniformly mapped to the target reporting field, realizes automatic extraction and reporting of the association relationship between fields, reduces the manual development and maintenance requirements for each data source, significantly reduces the development and maintenance costs, and at the same time improves the automation level and accuracy of data reporting, so that the applicability and ease of operation of the system in multi-source data scenarios have been significantly improved.

[0136] In this embodiment, the electronic device (eg Figure 1The 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.

[0137] It should be emphasized that in order to further ensure the privacy and security of the above financial data information, the above financial data information can also be stored in a blockchain node.

[0138] 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.

[0139] The embodiments of the present application 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.

[0140] 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.

[0141] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it 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).

[0142] 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.

[0143] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a financial data automatic reporting 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.

[0144] like Figure 3 As shown, the financial data automatic reporting device 300 described in this embodiment includes:

[0145] The data classification module 301 is used to obtain the original financial data and determine the data source corresponding to the original financial data using the pre-trained data classification model to obtain the target data source;

[0146] The data preparation module 302 is used to obtain a data processing rule engine and a target data reporting template that match the target data source, wherein the data processing rule engine includes data cleaning rules, data parsing rules, and data mapping rules;

[0147] A data cleaning module 303 is used to clean the original financial data based on data cleaning rules to obtain standardized data;

[0148] The data parsing module 304 is used to parse the standardized data using data parsing rules and extract target data source fields;

[0149] The data mapping module 305 is used to extract the association relationship between the target data source field and the target reporting field in the target data reporting template using the data mapping rule, obtain the field association relationship, and perform data field mapping according to the field association relationship;

[0150] The data reporting module 306 is used to fill in the target data source fields into the target data reporting template according to the data field mapping result to generate a financial data report.

[0151] Furthermore, the financial data automatic reporting device 300 also includes a model training module, which is specifically used for:

[0152] Acquire a pre-collected historical financial data set, wherein the historical financial data set includes financial historical data from several data sources and data source labels corresponding to each historical financial data; perform feature processing on the historical financial data to obtain historical financial data features; import the historical financial data features and data source labels into a pre-built initial classification model, and obtain the data source classification prediction results output by the model, wherein the initial classification model is built based on a random forest algorithm; iteratively update the initial classification model based on the data source classification prediction results to obtain a trained data classification model.

[0153] Furthermore, the model training module is further used to:

[0154] The historical financial data features are used as the input variables of the model, and the data source labels are used as the output variables of the model; the historical financial data features are randomly combined to obtain several feature matrices; a data source label is associated with each feature matrix to generate an associated feature matrix; each associated feature matrix is ​​sequentially imported into the decision tree of the initial classification model, and the node splitting purity value of each decision tree is calculated; according to the node splitting purity value of each decision tree, the data source classification prediction result is determined, and the data source classification prediction result is output.

[0155] Furthermore, the financial data automatic reporting device 300 also includes a rule engine and a template generation module, which are specifically used to:

[0156] The data processing logic corresponding to the financial historical data from several data sources is obtained, wherein the data processing logic includes data cleaning logic, data parsing logic and data mapping logic; the data cleaning logic, data parsing logic and data mapping logic are respectively transformed into rules to obtain data cleaning rules, data parsing rules and data mapping rules; a data processing rule engine corresponding to each data source is constructed based on the data cleaning rules, data parsing rules and data mapping rules; historical data reports corresponding to the financial historical data from several data sources are obtained, and fixed fields and reporting fields in the historical data reports are identified; and data reporting templates corresponding to each data source are generated according to the fixed fields and reporting fields in the historical data reports.

[0157] Furthermore, the data mapping module 305 is specifically used for:

[0158] Use data mapping rules to perform semantic recognition of target data source fields and target reporting fields respectively to obtain first field semantics and second field semantics; match target data source fields and target reporting fields based on the first field semantics and second field semantics, and generate field association relationships based on the field matching results; perform data field mapping of target data source fields and target reporting fields based on the field association relationships.

[0159] Furthermore, the financial data automatic reporting device 300 further includes a data conversion module, which is specifically used for:

[0160] Identify the data format of the target reporting field to obtain a first target data format; identify the data format of the target data source field to obtain a second target data format; determine whether the first target data format matches the second target data format; when the first target data format does not match the second target data format, use data conversion rules to convert the data format of the target data source field into the first target data format.

[0161] Furthermore, the financial data automatic reporting device 300 further includes a verification and correction module, which is specifically used for:

[0162] Use data verification rules to perform semantic recognition on target data source fields and fixed fields in financial data reports to obtain semantic recognition results; determine whether there are abnormalities in the data reporting of financial data reports based on the semantic recognition results; when there are abnormalities in the data reporting of financial data reports, use data correction rules combined with semantic recognition results and data field mapping results to re-report the financial data reports.

[0163] In the above embodiment, the present application discloses a financial data automatic reporting device, which belongs to the field of big data technology. The present application realizes automatic identification of the data source of the original financial data by introducing a pre-trained data classification model, and then automatically selects a matching data processing rule engine and reporting template according to the target data source, and standardizes the original data through data cleaning, parsing and mapping rules to ensure that data from different data sources can be uniformly mapped to the target reporting field, realizes automatic extraction and reporting of the association relationship between fields, reduces the manual development and maintenance requirements for each data source, significantly reduces the development and maintenance costs, and at the same time improves the automation level and accuracy of data reporting, so that the applicability and ease of operation of the system in multi-source data scenarios have been significantly improved.

[0164] 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.

[0165] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected and communicated through a system bus. It should be noted that the figure only shows a computer device 4 with a memory 41, a processor 42, and a network interface 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), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0166] 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.

[0167] 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, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. 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 automatic reporting method of financial data. 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.

[0168] 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 the computer-readable instructions stored in the memory 41 or process data, such as running the computer-readable instructions of the financial data automatic reporting method.

[0169] 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.

[0170] In the above embodiment, the present application discloses a computer device, which belongs to the field of big data technology. The present application realizes automatic identification of the data source of the original financial data by introducing a pre-trained data classification model, and then automatically selects a matching data processing rule engine and reporting template according to the target data source, and standardizes the original data through data cleaning, parsing and mapping rules to ensure that data from different data sources can be uniformly mapped to the target reporting field, realizes automatic extraction and reporting of the association relationship between fields, reduces the manual development and maintenance requirements for each data source, significantly reduces the development and maintenance costs, and at the same time improves the automation level and accuracy of data reporting, so that the applicability and ease of operation of the system in multi-source data scenarios have been significantly improved.

[0171] 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 automatic reporting method of financial data as described above.

[0172] In the above embodiment, the present application discloses a computer-readable storage medium, which belongs to the field of big data technology. The present application realizes automatic identification of the data source of the original financial data by introducing a pre-trained data classification model, and then automatically selects a matching data processing rule engine and reporting template according to the target data source, and standardizes the original data through data cleaning, parsing and mapping rules to ensure that data from different data sources can be uniformly mapped to the target reporting field, realizes automatic extraction and reporting of the association relationship between fields, reduces the manual development and maintenance requirements for each data source, significantly reduces the development and maintenance costs, and at the same time improves the automation level and accuracy of data reporting, so that the applicability and ease of operation of the system in multi-source data scenarios have been significantly improved.

[0173] 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.

[0174] 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 electronic devices, 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.

[0175] 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 automatically filling in financial data, characterized in that: include: Obtaining original financial data, and using a pre-trained data classification model to determine a data source corresponding to the original financial data, to obtain a target data source; Acquire a data processing rule engine and a target data reporting template that match the target data source, wherein the data processing rule engine includes data cleaning rules, data parsing rules, and data mapping rules; Performing data cleaning on the original financial data based on the data cleaning rules to obtain standardized data; Perform data parsing on the standardized data using the data parsing rules to extract target data source fields; Extracting associations between the target data source field and the target reporting field in the target data reporting template using the data mapping rule to obtain field associations, and performing data field mapping according to the field associations; According to the data field mapping result, the target data source field is filled into the target data reporting template to generate a financial data report.

2. The method for automatically filling in financial data according to claim 1, characterized in that: Before the step of obtaining the original financial data and using the pre-trained data classification model to determine the data source corresponding to the original financial data to obtain the target data source, the step further includes: Acquire a pre-collected historical financial data set, wherein the historical financial data set includes financial historical data from a plurality of data sources and a data source label corresponding to each historical financial data; Performing feature processing on the historical financial data to obtain features of the historical financial data; Importing the historical financial data features and the data source labels into a pre-built initial classification model, and obtaining the data source classification prediction result output by the model, wherein the initial classification model is built based on a random forest algorithm; The initial classification model is iteratively updated based on the data source classification prediction result to obtain the trained data classification model.

3. The method for automatically filling in financial data according to claim 2, characterized in that: The step of importing the historical financial data features and the data source labels into a pre-built initial classification model and obtaining the data source classification prediction result output by the model specifically includes: Using the historical financial data features as input variables of the model, and using the data source labels as output variables of the model; Randomly combining the historical financial data features to obtain a number of feature matrices; Associate a data source label with each feature matrix to generate an associated feature matrix; Importing each of the associated feature matrices into the decision tree of the initial classification model in sequence, and calculating the node splitting purity value of each of the decision trees; According to the node splitting purity value of each decision tree, the data source classification prediction result is determined, and the data source classification prediction result is output.

4. The method for automatically filling in financial data according to claim 2, characterized in that: Before the step of obtaining a data processing rule engine and a target data reporting template matching the target data source, the method further includes: Acquire data processing logic corresponding to financial historical data from several data sources, wherein the data processing logic includes data cleaning logic, data parsing logic and data mapping logic; Performing rule transformation on the data cleaning logic, the data parsing logic and the data mapping logic respectively to obtain the data cleaning rule, the data parsing rule and the data mapping rule; Building a data processing rule engine corresponding to each data source based on the data cleaning rule, the data parsing rule and the data mapping rule; Obtaining historical data reports corresponding to financial historical data from a plurality of data sources, and identifying fixed fields and reporting fields in the historical data reports; According to the fixed fields and reporting fields in the historical data report, a data reporting template corresponding to each data source is generated.

5. The method for automatically filling in financial data according to claim 1, characterized in that: The step of using the data mapping rule to extract the association relationship between the target data source field and the target reporting field in the target data reporting template to obtain the field association relationship, and performing data field mapping according to the field association relationship specifically includes: Using the data mapping rule, semantic recognition is performed on the target data source field and the target reporting field to obtain the first field semantics and the second field semantics; Matching the target data source field and the target reporting field according to the first field semantics and the second field semantics, and generating the field association relationship according to the field matching result; Data field mapping between the target data source field and the target reporting field is performed according to the field association relationship.

6. The method for automatically filling in financial data according to claim 1, characterized in that: The data processing rule engine further includes a data conversion rule, and after the step of using the data mapping rule to extract the association relationship between the target data source field and the target reporting field in the target data reporting template to obtain the field association relationship, and performing data field mapping according to the field association relationship, further includes: Identify the data format of the target reporting field to obtain a first target data format; Identify the data format of the target data source field to obtain a second target data format; determining whether the first target data format matches the second target data format; When the first target data format does not match the second target data format, the data format of the target data source field is converted into the first target data format using the data conversion rule.

7. The method for automatically filling in financial data according to claim 4, characterized in that: The data processing rule engine further includes data verification rules and data correction rules. After the step of filling the target data source field into the target data reporting template according to the data field mapping result to generate a financial data report, it also includes: Using the data verification rules to perform semantic recognition on the target data source fields and fixed fields in the financial data report to obtain semantic recognition results; Determine whether there is any abnormality in the data filling of the financial data report according to the semantic recognition result; When there is an abnormality in the data reporting of the financial data report, the financial data report is re-reported using a data correction rule in combination with the semantic recognition result and the data field mapping result.

8. A financial data automatic reporting device, characterized in that: include: A data classification module is used to obtain raw financial data and use a pre-trained data classification model to determine a data source corresponding to the raw financial data to obtain a target data source; A data preparation module, used to obtain a data processing rule engine and a target data reporting template that match the target data source, wherein the data processing rule engine includes data cleaning rules, data parsing rules and data mapping rules; A data cleaning module, used to clean the original financial data based on the data cleaning rules to obtain standardized data; A data parsing module, used to parse the standardized data using the data parsing rules and extract target data source fields; A data mapping module, used to extract the association relationship between the target data source field and the target reporting field in the target data reporting template using the data mapping rule, obtain the field association relationship, and perform data field mapping according to the field association relationship; The data reporting module is used to fill in the target data source fields into the target data reporting template according to the data field mapping result to generate a financial data report.

9. A computer device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the method for automatically filling in financial data as claimed in any one of claims 1 to 7 are implemented.

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 method for automatically filling in financial data according to any one of claims 1 to 7.

Images