A method, system, device and medium for processing account period data based on Microsoft 365

Abstract

The present invention relates to the technical field of financial data processing, and in particular to a method, system, device and medium for processing account period data based on Microsoft 365. The method specifically comprises: after performing data cleaning and data conversion on account period data in multiple Excel files based on the Power Query function of Microsoft 365, an account period data model is constructed according to the association relationship between the account period data in multiple Excel files; after data visualization of the account period data model, an account period data report is obtained, and the account period data report is intelligently analyzed using the Copilot plug-in of Microsoft 365 to obtain an account period data analysis result; after data classification of the account period data analysis result, different categories of account period data analysis results are obtained, and different categories of account period data analysis results are distributed to corresponding staff members through pre-set personnel permissions. The present invention improves the efficiency and accuracy of financial data management and strengthens data security and access control.

Description

Technical Field

[0001] The present invention relates to the technical field of financial data processing, and in particular to an account period data processing method, system, device and medium based on Microsoft 365. Background Art

[0002] With the rapid expansion of enterprise scale and the increasing complexity of business, account period data processing plays a vital role in enterprise financial management. Account period data, especially management and legal reporting data, is not only a direct reflection of the enterprise's operating conditions, but also an important basis for financial analysis and decision-making.

[0003] Traditional methods of processing account period data mostly rely on manual operations and simple data processing tools, such as Excel. This processing method can still meet the needs in scenarios with small data volumes and simple businesses, but as the scale of enterprises expands and the complexity of businesses increases, its limitations gradually become apparent. Manual processing is inefficient, prone to errors, and difficult to cope with large-scale and complex data processing needs. In addition, this method can often only provide basic data collation and simple analysis, and cannot meet the diversified and personalized needs of enterprises for data processing.

[0004] Although there are some financial management software on the market that can support the processing and analysis of account period data, these software usually have limitations. On the one hand, they are often limited to specific data processing methods and report forms, and cannot flexibly adapt to the actual needs of enterprises. On the other hand, these software often lack intelligent analysis functions and cannot deeply mine valuable information and insights from account period data, thus limiting their application in financial analysis and decision support.

[0005] Take the Fone system as an example. As the core system of the current financial system to realize the monthly settlement of management / legal accounts and generate vouchers, although it provides basic account period data processing functions for enterprises, users still need to download management and legal report data to the local computer and perform forecast analysis, operation analysis and other operations through tools such as Excel. This not only increases the user's operating burden, but also reduces the efficiency and accuracy of data processing. Summary of the invention

[0006] The object of the present invention is to provide a method, system, device and medium for processing account period data based on Microsoft 365, which improves the efficiency and accuracy of financial data management, strengthens data security and access control, and solves at least one of the above-mentioned prior art problems.

[0007] In a first aspect, the present invention provides a method for processing account period data based on Microsoft 365, the method specifically comprising:

[0008] Based on the data interface of the financial data management system, the account period data is obtained, and the account period data is imported into the Excel file through the preset data mapping rules, wherein the account period data includes the management report data and the legal report data;

[0009] After cleaning and converting the account period data in multiple Excel files based on the Power Query function of Microsoft 365, a account period data model is constructed based on the association between the account period data in multiple Excel files;

[0010] After data visualization of the account period data model, an account period data report is obtained, and the account period data report is intelligently analyzed using the Copilot plug-in of Microsoft 365 to obtain an account period data analysis result;

[0011] The account period data analysis results are classified into different categories of account period data analysis results, and the different categories of account period data analysis results are distributed to corresponding staff members through preset personnel authority.

[0012] In a second aspect, the present invention provides an account period data processing system based on Microsoft 365, the system specifically comprising:

[0013] A first processing module is used to obtain account period data based on a data interface of a financial data management system, and import the account period data into an Excel file according to a preset data mapping rule, wherein the account period data includes management reporting data and legal reporting data;

[0014] The second processing module is used to clean and convert the account period data in multiple Excel files based on the Power Query function of Microsoft 365, and then build an account period data model according to the correlation between the account period data in multiple Excel files;

[0015] A third processing module is used to obtain an account period data report after data visualization of the account period data model, and to perform intelligent analysis on the account period data report using the Copilot plug-in of Microsoft 365 to obtain an account period data analysis result;

[0016] The fourth processing module is used to obtain different categories of account period data analysis results by classifying the account period data analysis results, and distribute the different categories of account period data analysis results to corresponding staff members through preset personnel permissions.

[0017] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor and a computer program stored in the memory, and when the computer program is executed on the processor, it implements the account period data processing method based on Microsoft 365 as described in any one of the above methods.

[0018] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for processing account period data based on Microsoft 365 as described in any one of the above methods is implemented.

[0019] Compared with the prior art, the present invention has at least one of the following technical effects:

[0020] 1. It improves the efficiency and accuracy of financial data management, strengthens data security and access control, and supports the decision-making process through intelligent data analysis. It is particularly suitable for enterprises that need to process and analyze large amounts of financial data scattered in multiple files, and can significantly improve the automation level of data processing and the application value of analysis results.

[0021] 2. Through refined classification of the data analysis results during the reconciliation period and combined with pre-set personnel permissions, data distribution to different staff members is achieved, ensuring the security and compliance of the data. This can meet the data needs of different staff members, improve data utilization efficiency, and also promote collaboration and communication within the enterprise.

[0022] 3. By analyzing the correlation between account period data, using association rule mining algorithm and data cube technology, a multi-dimensional account period data model was constructed. The construction of the account period data model helps reveal the intrinsic connection between different data files and provides structured support for in-depth analysis.

[0023] 4. Through the combination of advanced technologies such as regular expressions, graph neural network models and support vector machine models, the refined cleaning and repair of reconciliation period data is achieved, ensuring the accuracy and completeness of the data.

[0024] 5. The Copilot plug-in of Microsoft 365 is used to realize intelligent analysis of the account period data report. Through natural language processing, semantic analysis, clustering algorithm and attention mechanism, key information in the account period data report is extracted and a comprehensive semantic vector representation is formed, which can provide a deeper understanding of the business meaning of the account period data report and improve the accuracy and efficiency of data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0026] Figure 1 It is a flowchart of a method for processing account period data based on Microsoft 365 provided by an embodiment of the present invention;

[0027] Figure 2 It is a structural diagram of a billing period data processing system based on Microsoft 365 provided in one embodiment of the present invention;

[0028] Figure 3 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0030] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0031] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0032] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0033] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0034] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0035] In the embodiment of the present application, the execution subject of the process includes a terminal device, which includes but is not limited to: a server, a computer, a smart phone, a tablet computer, and other devices capable of executing the method disclosed in the present application. Figure 1 A flowchart of a method for processing account period data based on Microsoft 365 disclosed in an embodiment of the present invention is shown, and the details are as follows:

[0036] S101, based on the data interface of the financial data management system, obtaining account period data, and importing the account period data into an Excel file through a preset data mapping rule, the account period data including management reporting data and legal reporting data.

[0037] In this embodiment, the financial data management system is a Fone system. In the Fone system, an interface specifically used for exporting account period data is configured. The interface needs to be able to retrieve management reporting data and legal reporting data from the database according to the preset data format and fields. Management reporting data usually refers to the financial data required for internal management reports, while legal reporting data refers to financial data that meets external legal, tax and other regulatory requirements. In the Excel file, the table structure is designed in advance, and the fields and formats that need to be filled are determined. Then, according to the account period data format exported from the Fone system, a set of data mapping rules is formulated. This set of rules needs to clarify which cell in the Excel table each field in the Fone system corresponds to, as well as possible data type conversion and format adjustment.

[0038] Export the account period data regularly (such as daily, weekly or monthly) through the data interface of the Fone system. The exported data can be in CSV, XML or other data formats that are easy to process. Then, use a programming script (such as a Python script) or a special data conversion tool to import the exported account period data into an Excel file according to the preset data mapping rules. During the import process, the field matching, type conversion and format adjustment of the data can be automatically completed. After the import is completed, verify the data in the Excel file to ensure the accuracy and completeness of the data. If the data is found to be abnormal or wrong, it can be corrected according to the original data in the Fone system. At the same time, the corrected data can also be re-imported into the Fone system to maintain data consistency.

[0039] In this embodiment, the time and effort of manual data processing are greatly reduced through the automated data export, import and verification process, thereby improving data processing efficiency. At the same time, since the data mapping rules are pre-set, data errors caused by human operation errors can be avoided. In addition, since strict verification and correction are performed during the data export and import process, it can be ensured that the data in the Excel file is consistent with the original data in the Fone system, thereby ensuring the accuracy of the data.

[0040] In some embodiments, in the above step S101, the importing of the account period data into an Excel file according to a preset data mapping rule specifically includes:

[0041] Using regular expressions to verify and clean the data format of the account period data in the Excel file to obtain standardized account period data;

[0042] Analyze the standardized account period data according to an association rule mining algorithm to obtain the association relationship of the standardized account period data and form a data chain;

[0043] Based on the data chain, a graph neural network model is used to extract features of the standardized account period data to obtain a data feature vector;

[0044] Using a support vector machine model to process the data feature vector, determine abnormal data or incomplete data in the standardized account period data, and perform data repair on the abnormal data or incomplete data in the standardized account period data;

[0045] Based on data types and business rules, the standardized account period data after data repair is classified according to the decision tree model and mapped to the specified location in the Excel file;

[0046] The standardized account period data in the Excel file is verified according to the convolutional neural network, and a data quality report is generated through feature matching and similarity calculation.

[0047] In this embodiment, according to the predefined data mapping rules, the account period data of each account period is obtained through the data interface of the Fone system. The acquired data is classified and processed by a decision tree model, and the data is automatically mapped to the specified position in the corresponding Excel template file according to the data type and business rules. In the data mapping process, the data format is verified using regular expressions, and the data that does not meet the format requirements is marked and cleaned. Through data cleaning and conversion, the original data is converted into standardized structured data. According to business needs, the structured data is analyzed using an association rule mining algorithm to discover the association relationship and pattern between the data. Using the discovered association relationship, a logical relationship network between the data is constructed to form a data chain. Based on the data chain, the graph neural network model is used to further extract features and represent the data to obtain a low-dimensional vector representation of the data. The extracted data feature vector is stored in the corresponding field in the Excel template file. Through the data feature vector, the support vector machine model is used to classify and predict the data to determine the integrity and accuracy of the data. For data determined to be abnormal or incomplete, the data interpolation and data synthesis methods are used to repair and fill the data to ensure the quality of the data. The repaired data is updated to the Excel template file to complete the automatic collection and storage of data. Finally, a convolutional neural network is used to perform a secondary check on the data in the Excel template file, verifying the consistency and accuracy of the data through feature matching and similarity calculation. Based on the check results, a data quality report is generated to identify potential data problems and anomalies, providing a high-quality data foundation for subsequent data analysis and application.

[0048] For example, the account period data of each account period is obtained through the data interface of the Fone system, and the obtained data is classified and processed using a decision tree model. For example, the data type is divided into financial data, business data, etc., and then the financial data is mapped to the corresponding positions of the balance sheet, income statement, etc. in the Excel template file according to the business rules. The regular expression "^\d+(\。\d+)?$" is used to verify the data format, and the data that does not meet the format requirements is marked and cleaned, such as converting "1,000" to "1000". The Apriori association rule mining algorithm is used to analyze the structured data with parameters of minimum support 05 and minimum confidence 8, and association rules such as "operating income growth 10% → net profit growth 8%" are found. A data chain is constructed based on association rules, and a graph neural network model is used to extract features and represent data, and a 64-dimensional data feature vector is obtained through node embedding. The extracted data feature vector is stored in the corresponding field of the Excel template file, such as the operating income feature vector is stored in the operating_income_features field of the income statement. The support vector machine model is used to classify the data, and the completeness and accuracy of the data are judged by the feature vector. For data that is judged to be abnormal or incomplete, the data interpolation method is used to repair it. For example, the missing operating cost data is filled in by the linear interpolation method based on the business knowledge that the gross profit margin is between 30% and 35%. Finally, the convolutional neural network is used to perform a secondary check on the data in the Excel template file, and the consistency of the data is verified through feature matching and cosine similarity calculation, and a data quality report is generated to provide a high-quality data foundation for subsequent data analysis and application.

[0049] Specifically, the method of using regular expressions to verify and clean the data format of the account period data in the Excel file to obtain standardized account period data includes: according to the account period data that does not conform to the standard format, using regular expressions to extract the year, month, and day information in the account period data, and obtaining logical year, month, and day data by judging whether the extracted year, month, and day are within a reasonable range; according to the logical year, month, and day data, using string concatenation to obtain a standardized account period data format, and obtaining standardized account period data by concatenating the year, month, and day data in a unified format; according to the standardized account period data, using data replacement to replace the original account period data with the standardized account period data, so as to obtain an Excel file in which all account period data are in a standard format.

[0050] Specifically, the standardized account period data is analyzed according to the association rule mining algorithm to obtain the association relationship of the standardized account period data and form a data chain, including: according to the standardized account period data, using the association rule mining algorithm to obtain the association relationship between different attributes in the standardized account period data, and obtaining the association rules between the attributes by analyzing the support, confidence and other indicators between the attributes; according to the obtained association rules, using the graph theory method, taking the attributes as nodes and the association rules as directed edges, constructing an attribute association directed graph, and intuitively representing the association relationship between the attributes in the form of a directed graph; according to the attribute association directed graph, using the depth-first search algorithm, starting from the attribute node with the highest association, traversing the directed graph, obtaining the attribute chain connected by the association rules, and forming a data chain, the data chain represents the association transmission relationship between the attributes; according to the formed data chain, using Use pattern matching algorithm to determine whether the data chain meets the preset association pattern. The preset association pattern is determined by business rules. The association pattern can be a continuous attribute chain or a circular attribute chain. According to the results of pattern matching, statistical methods are used to obtain the distribution characteristics of the data chain that meets the preset association pattern. By analyzing indicators such as the length of the data chain and the number of attributes covered, the association strength and association breadth of the data chain are determined. According to the distribution characteristics of the data chain, a machine learning algorithm is used to build a classification model of the data chain. Through the classification model, it can be determined whether the new standardized account period data meets the preset association pattern and the association characteristics of the new data are obtained. According to the association characteristics of the data chain, business rules are used to interpret and apply the data chain. Through the data chain, the business rules hidden in the standardized account period data can be discovered to guide business decisions, optimize business processes, and improve business efficiency.

[0051] Specifically, based on the data chain, the graph neural network model is used to extract features from the standardized account period data to obtain a data feature vector, including: according to the transaction data, user portrait data, product information data, etc. in the data chain, the original data is cleaned, converted and integrated using data preprocessing technology to obtain standardized account period data. By constructing a graph neural network model, the user nodes, product nodes, transaction behavior edges, etc. in the standardized account period data are mapped to a graph structure to obtain a graph data representation. The graph convolutional neural network algorithm is used to extract features and represent graph data, and the high-dimensional semantic features of the nodes are obtained through multi-layer convolution and pooling operations. Through the graph attention mechanism, the weights of the node features are dynamically adjusted according to the connection relationship and interaction behavior between the nodes to obtain a more accurate and rich data feature vector.

[0052] Specifically, the method of using a support vector machine model to process the data feature vector, determine abnormal data or incomplete data in the standardized account period data, and perform data repair on the abnormal data or incomplete data in the standardized account period data includes: obtaining the data feature vector in the standardized account period data, extracting key attributes of the account period data such as the account period date, the account period amount, etc., to construct the data feature vector as the input of the support vector machine model. The support vector machine model is used to train the data feature vector, and the classification boundary of abnormal data and incomplete data is established by setting appropriate kernel functions and penalty parameters to obtain a trained support vector machine model. According to the trained support vector machine model, the feature vector of each data in the standardized account period data is predicted and classified to determine whether it belongs to abnormal data or incomplete data, and the account period data that needs to be repaired is determined. For the account period determined to be abnormal data or incomplete data, the corresponding data repair strategy is used for processing. According to the business attributes of the account period data, the missing values ​​are estimated by interpolation, regression and other methods, or the abnormal values ​​are corrected according to historical data and business rules to obtain the repaired complete account period data. The repaired account period data is added back to the standardized account period data, the data feature vector is updated, and the data is verified again through the support vector machine model to ensure that the repaired data meets the business requirements and data quality standards. The above data repair steps are iterated until all abnormal data and incomplete data in the standardized account period data are effectively repaired, and a high-quality account period data set is obtained to provide reliable data support for subsequent business analysis and decision-making.

[0053] Specifically, based on the data type and business rules, the standardized account period data after data repair is classified according to the decision tree model and then mapped to the specified position in the Excel file, including: according to the data type and business rules of the standardized account period data, the decision tree model is used to classify the data, obtain the classification results, and obtain the classification label corresponding to each data. By analyzing the structure and business requirements of the Excel file, the mapping position of the classification result in the Excel file is determined, and the row and column coordinates in the Excel file corresponding to each classification label are obtained. According to the standardized account period data after data repair, the pandas library of Python is used to read the data, and the values ​​of each field of each data are obtained to obtain a complete data record. By matching each data record with its corresponding classification label, the target position of the data record in the Excel file is obtained, and the row and column coordinates of the data record in the Excel file are determined. According to the field value of the data record and the corresponding row and column coordinates of the Excel file, the openpyxl library of Python is used to write the data to the specified position of the Excel file to obtain an Excel file filled with classified data. By checking and verifying the Excel file filled with classified data, it is determined whether the data mapping is correct and complete, and the accuracy and completeness of the data mapping are determined. According to business needs and data mapping results, use Excel's formatting function to adjust the style of the mapped data, obtain an Excel file that meets business display requirements, and get the final data classification mapping results.

[0054] Specifically, the standardized account period data in the Excel file is verified according to the convolutional neural network, and a data quality report is generated through feature matching and similarity calculation, including:

[0055] Obtain standardized account period data from the Excel file, convert the account period data into a format suitable for convolutional neural network input through data preprocessing, and obtain the feature representation of the account period data. Design the network structure of the convolutional neural network according to the business attributes of the account period data, use multi-layer convolution and pooling layers to extract local features of the account period data, and map the features to the category space of the standard account period through the fully connected layer. By constructing a training set and a test set of the account period data, train the convolutional neural network model using supervised learning, so that the model can learn the feature representation and classification rules of the account period data, and obtain a trained account period verification model. For the account period data to be verified, obtain its feature representation through data preprocessing, and input it into the trained convolutional neural network model, and obtain the predicted category of the account period data through forward propagation calculation. According to the difference between the predicted category and the actual standard account period, use similarity calculation methods such as Euclidean distance or cosine similarity to judge the matching degree between the account period to be verified and the standard account period, and obtain the quality assessment result of the account period data. All account period data to be verified are evaluated one by one, and the quality assessment results are summarized. By setting quality thresholds, the overall quality level of the account period data is judged, and a data quality report is generated to provide a basis for financial data analysis and decision-making.

[0056] S102, after performing data cleaning and data conversion on the account period data in multiple Excel files based on the Power Query function of Microsoft 365, build an account period data model according to the correlation between the account period data in multiple Excel files.

[0057] In this embodiment, multiple Excel files are connected through Power Query to obtain the account period data in each Excel file. Then, the data type of the obtained account period data is converted, and the text type data is converted into a numeric type or a date type. Next, the converted account period data is cleaned, duplicate data is removed, missing values ​​are filled, and outliers are processed. After the account period data cleaning and conversion are completed, the account period data model is constructed using data modeling technology based on the correlation between the account period data.

[0058] In this embodiment, the data processing efficiency is significantly improved and manual intervention and errors are reduced through the automated data import, cleaning, conversion and association process. Through the merge query function of Power Query, the association between the account period data in multiple Excel files can be easily achieved, which facilitates subsequent data analysis and modeling.

[0059] In some embodiments, in the above step S102, the constructing of the account period data model according to the association relationship between the account period data in the multiple Excel files specifically includes:

[0060] By analyzing the association between the account period data in multiple Excel files, a fact table and a dimension table are determined, wherein the fact table includes the measurement values ​​of the account period data, and the plurality of dimension tables include the dimension attributes of the account period data;

[0061] Establish the association between the fact table and the dimension table through the primary key and foreign key to form the first account period data model;

[0062] mining association rules between the account period data in the first account period data model according to an association rule mining algorithm to obtain a second account period data model;

[0063] Using data cube technology to perform multi-dimensional analysis on the second account period data model to obtain a third account period data model;

[0064] The account period data in the third account period data model is predicted and analyzed according to a time series analysis algorithm to obtain a target account period data model.

[0065] In this embodiment, the fact table and dimension table in the data model are determined by analyzing the association relationship between the account period data. Among them, the fact table contains the measurement values ​​of the account period data, such as sales, cost, etc.; the dimension table contains the dimension attributes of the account period data, such as time, region, product, etc. Then, the association relationship between the fact table and the dimension table is established through the primary key and the foreign key to form a data model of a star schema or a snowflake schema. When constructing the data model, an association rule mining algorithm, such as the Apriori algorithm or the FP-growth algorithm, is used to mine the association rules between the account period data. Through the association rule mining algorithm, frequent item sets and association rules are obtained to reveal the hidden relationships and patterns between the account period data. At the same time, the data cube technology is used to perform multi-dimensional analysis on the data model to generate a data cube containing multiple dimensions and measurements. Through the data cube, multi-dimensional analysis operations such as drilling, slicing, and rotation can be performed to deeply explore the laws and trends of the account period data. Finally, the constructed account period data model is imported into PowerBI to create interactive visual reports and dashboards. Through the visualization function of PowerBI, the key indicators and trends of the account period data are presented in the form of charts, maps, matrices, etc., to achieve multi-dimensional analysis and exploration of the account period data. At the same time, time series analysis algorithms, such as ARIMA model or Prophet model, are used to perform time series forecasts on the account period data, predict future sales, costs and other key indicators, and provide reference for corporate decision-making.

[0066] For example, after completing data cleaning and conversion, a star data model containing one fact table and four dimension tables was constructed based on the business relationship of the account period data. The fact table contains measurement values ​​such as sales and cost, and the dimension table contains dimension attributes such as time, region, product, and customer. The Apriori algorithm was used to mine association rules for 10,000 records in the fact table, setting the minimum support to 05 and the minimum confidence to 8. 50 frequent item sets and 20 association rules were obtained, and some interesting patterns were found, such as some products are often purchased at the same time, and the sales in some regions are related to specific time periods. At the same time, using data cube technology, a three-dimensional data cube was constructed based on the three dimensions of time, region, and product and one measurement of sales, which can slice, drill, rotate, and perform multi-dimensional analysis on the data from different dimensional perspectives. Finally, the data model was imported into PowerBI, and five interactive dashboards were created, showing key indicators such as the time trend, regional distribution, and product proportion of sales through visualization methods such as bar charts, line charts, and maps. The ARIMA time series model is used to predict sales in the next three months based on the historical sales data of the past 12 months, with an average absolute percentage error of 5%, providing companies with a reliable decision-making reference.

[0067] Specifically, the method of determining the fact table and the dimension table by analyzing the association between the account period data in multiple Excel files includes: obtaining the account period data in multiple Excel files, and determining the dimension attributes and measurement values ​​in the account period data by analyzing the field attributes and data content in the account period data. According to the dimension attributes in the determined account period data, a star model with the account period as the theme is designed by using a data modeling method to determine the fact table and the dimension table. By analyzing the measurement values ​​in the account period data, the measurement values ​​are used as the measurement fields of the fact table, and the measurement values ​​are generally numerical and used for statistical analysis. According to the dimension attributes in the account period data, multiple dimension tables related to the account period are designed, and each dimension table represents an angle for analyzing the account period data, such as the time dimension, the regional dimension, the product dimension, etc. By analyzing the association between the dimension attributes and the measurement values ​​in the account period data, the key relationship between the fact table and the dimension table is determined, and the primary key and the foreign key are used to connect the fact table and the dimension table. The account period data is loaded into the designed fact table and dimension table by using an ETL tool or programming method to complete the construction of the data warehouse.

[0068] Specifically, the association relationship between the fact table and the dimension table is established through the primary key and the foreign key to form the first account period data model, including: determining the business process and measurement values ​​in the fact table by analyzing business needs, such as sales volume, sales volume and other measurements in the sales fact table. According to the dimension foreign key in the fact table, relevant dimension information is obtained, such as time, region, product and other dimension tables. The association relationship between the fact table and the dimension table is established by using the primary key and foreign key constraints. For example, the time foreign key of the sales fact table is associated with the primary key of the time dimension table, and the region foreign key is associated with the primary key of the region dimension table. By establishing the association between the tables, a star model or snowflake model structure is obtained, forming a data model with the fact table as the center and the dimension tables surrounding it.

[0069] Specifically, the method of using data cube technology to perform multi-dimensional analysis and processing on the second account period data model to obtain the third account period data model includes: according to the second account period data model, using data extraction technology to obtain multi-dimensional data related to the account period, including account period time, account balance, customer information, etc., to form a fact table and dimension table of the data cube. By performing aggregation calculation on the account balance data in the fact table, the summary data under different dimensional combinations are obtained, such as grouping by account period time and customer to calculate the receivable and payable balance of each customer in each account period. Using slicing operation to select a data subset of a specific account period, such as intercepting the data of the most recent year to obtain the account data cube within the time range. By rotating operation, the order and hierarchy of dimensions are adjusted, such as adjusting the customer dimension to above the account period dimension to form a multi-account period data view with customers as the main body. According to business needs, using drilling operation to roll up and drill down the data cube to obtain data of different granularities, such as drilling down from annual account period data to monthly account period data, to reveal the details of account changes. Through slicing and rotation operations, we can obtain combined views of different dimensions, such as cross-analysis of customer dimension and account period dimension, to determine the trend of changes in accounts receivable and payable of each customer in different account periods. By calculating derivative indicators, we can add new metrics to the data cube, such as aging analysis indicators, to evaluate the quality and recovery risk of accounts receivable through the aging distribution of accounts receivable. According to business rules, we can identify and clean up outliers and erroneous data in the data cube, such as eliminating data with account period time beyond the normal range to ensure the accuracy and reliability of the data. Through multi-dimensional data analysis and exploration, we can reveal the hidden patterns and trends in the accounting data, such as finding that the accounts receivable turnover rate of some customers continues to decline, indicating potential collection risks. Finally, the data cube processed by multi-dimensional analysis is used as the third account period data model to provide comprehensive, accurate and multi-angle data support for subsequent financial decision-making and risk management.

[0070] Specifically, the method of performing a forecast analysis on the account period data in the third account period data model according to a time series analysis algorithm to obtain a target account period data model includes: performing a forecast analysis on the account period data according to the account period data in the third account period data model using a time series analysis algorithm to obtain a historical change trend of the account period data. By analyzing the historical change trend of the account period data, a forecast value of the account period data in a future period is obtained. According to the predicted future change of the account period data, the forecast model parameters of the account period data of the target account period are determined. The forecast calculation of the account period data of the target account period is performed using the determined target account period data forecast model parameters to obtain the forecast account period data of the target account period. The forecast account period data of the target account period is used as the account period data of the target account period data model to obtain a complete target account period data model. The accuracy of the target account period data model is judged by comparing the account period data in the target account period data model with the corresponding account period data in the third account period data model. According to the accuracy judgment result of the target account period data model, the relevant parameters in the forecast analysis process are optimized and adjusted to obtain the optimized target account period data model.

[0071] In a possible implementation manner, mining association rules between the account period data in the first account period data model according to an association rule mining algorithm specifically includes:

[0072] Acquire multiple account period attributes of the account period data in the first account period data model to form an initial data set;

[0073] Obtaining a first frequent itemset by counting the support of each account period attribute in the initial data set, wherein the first frequent itemset is a set of account period attributes whose support is greater than or equal to a minimum support threshold;

[0074] Generate a candidate payment period attribute pair by connecting every two payment period attributes in the first frequent item set;

[0075] By counting the support of each candidate account period attribute pair, a second frequent item set is obtained, where the second frequent item set is a set of candidate account period attribute pairs whose support is greater than or equal to a minimum support threshold;

[0076] Repeat the steps of generating the candidate account period attribute pairs and generating the second frequent item set until no higher-order frequent item sets can be generated, thereby obtaining a kth frequent item set;

[0077] The confidence of each frequent item set in the kth frequent item set is calculated to obtain an association rule, where the association rule is an implied relationship between frequent item sets whose confidence is greater than or equal to a minimum confidence threshold.

[0078] In this embodiment, first, multiple account period attributes of the account period data, such as the account period amount, the account period time, the account period status, etc., are obtained from the first account period data model to form an initial data set. Then, by counting the support of each account period attribute in the initial data set, for example, the support of the account period amount greater than 1,000 yuan is 80%, the support of the account period time within 30 days is 75%, and the support of the account period status is 90%, the account period attributes with a support greater than or equal to the minimum support threshold (such as 60%) are screened out to form a first frequent item set. Then, every two account period attributes in the first frequent item set are connected by a connection operation to generate candidate account period attribute pairs, such as (account period amount greater than 1,000 yuan, account period time within 30 days), (account period amount greater than 1,000 yuan, account period status is normal), etc., and by counting the support of each candidate account period attribute pair, the candidate account period attribute pairs with a support greater than or equal to the minimum support threshold are screened out to form a second frequent item set. Repeat the above steps of generating candidate account period attribute pairs and frequent item sets until no higher-order frequent item sets can be generated, and finally obtain the kth frequent item set. Finally, calculate the confidence of each frequent item set in the kth frequent item set, for example, the confidence of (account period amount is greater than 1,000 yuan → account period status is normal) is 90%, and the implicit relationship between frequent item sets with confidence greater than or equal to the minimum confidence threshold (such as 80%) is screened out to form association rules. By analyzing the association rules, the association pattern between account period attributes is judged, such as accounts with longer overdue days usually have larger account period amounts, accounts with account period status of "bad debt" usually have longer overdue days, etc., and valuable association patterns in account period data are obtained. According to the obtained association patterns, predictions and decisions are made on account period data, such as predicting the account period amount of accounts with longer overdue days, judging the overdue days of accounts with "bad debt" status, etc., to provide data support and decision-making basis for account period management.

[0079] S103, after data visualization of the account period data model, an account period data report is obtained, and the account period data report is intelligently analyzed using the Copilot plug-in of Microsoft 365 to obtain an account period data analysis result.

[0080] In this embodiment, in Microsoft Excel, various charts such as bar charts, line charts, pie charts, etc. are created according to the account period data model using built-in chart tools or advanced visualization tools such as Power BI to intuitively display the account period data.

[0081] In another possible implementation, the method of obtaining an account period data report after data visualization of the account period data model further includes: writing an automated script program according to the account period data model using the Visual Basic for Applications programming language. The account period data model is obtained through the script program, and the relevant data of the account period data model is automatically filled into the corresponding PowerPoint slide according to the preset PowerPoint template format and layout requirements. During the filling process, a heuristic search algorithm is used to search for the preset position in the PowerPoint template, and the account period data model is matched with the preset position. The type and format of the account period data model are judged by the pattern matching algorithm, and the account period data model is filled into the matching preset position according to the judgment result. After the filling is completed, the text content in the account period data report is automatically generated by the text generation algorithm, and the generated text content is filled into the corresponding slide. The chart content in the account period data report is automatically generated by the image generation algorithm, and the generated chart content is filled into the corresponding slide. During the filling process, a constraint satisfaction algorithm is used to determine whether the filled content meets the format and layout requirements of the PowerPoint template. If the requirements are not met, the filled content is adjusted by the back propagation algorithm until the requirements are met. After filling is completed, the quality and consistency of the generated account period data report are evaluated through the heuristic evaluation algorithm, and the report is optimized and adjusted according to the evaluation results, and finally a standardized account period data report is generated. By applying the above algorithms and programming techniques, the account period data model can be automatically filled into the PowerPoint template to generate a standardized account period data report.

[0082] In this embodiment, the combination of data visualization and Copilot intelligent analysis can significantly improve the efficiency of data analysis. The automated and intelligent analysis process reduces the time and effort of manual operation, allowing users to obtain account period data analysis results more quickly.

[0083] In some embodiments, in the above step S103, the use of the Microsoft 365 Copilot plug-in to perform intelligent analysis on the account period data report to obtain the account period data analysis results specifically includes:

[0084] Using a natural language processing model in the Copilot plug-in of Microsoft 365, preprocessing the text content of the account period data report is performed to obtain a structured representation of the account period data report;

[0085] By performing semantic analysis on the structured representation, a vector representation of each semantic unit of the account period data report is obtained, wherein the vector representation includes a semantic vector of each business attribute of the account period data report;

[0086] Based on the cosine similarity algorithm, the similarity between the semantic units of the account period data report is calculated to obtain a similarity matrix;

[0087] Based on the similarity matrix, a clustering algorithm is used to cluster the semantic units of the account period data report to obtain semantic clusters representing different business attributes;

[0088] By performing keyword extraction and topic model analysis on the semantic units in each semantic cluster, the business attribute label represented by each semantic cluster is obtained;

[0089] Based on the business attribute label of each semantic cluster and the vector representation of each semantic unit, an attention mechanism is used to weight the importance of each semantic unit to obtain a comprehensive semantic vector representation of each business attribute of the account period data report;

[0090] The account period data analysis result is obtained by splicing the comprehensive semantic vectors of various business attributes of the account period data report.

[0091] In this embodiment, the natural language processing model in the Copilot plug-in of Microsoft 365 is first used to perform word segmentation, part-of-speech tagging, named entity recognition and other preprocessing on the text content of the account period data report to obtain a structured representation of the report. Then, the structured representation is converted into a 300-dimensional semantic vector of each semantic unit through a word embedding algorithm such as Word2Vec, including semantic vectors of business attributes such as reported sales, profit margin, debt-to-asset ratio, etc. Then, the cosine similarity algorithm is used to calculate the similarity between semantic units, such as obtaining a 1000×1000 symmetric similarity matrix. Based on this matrix, the K-Means clustering algorithm is used to cluster 1000 semantic units into 20 semantic clusters, each cluster representing a class of business attributes. For each semantic cluster, the 10 keywords with the highest TF-IDF weight are extracted, and 5 subject words are extracted using the LDA topic model to comprehensively determine the business attribute labels of the cluster, such as "income situation", "cost management", etc. Finally, the attention mechanism is used to assign a weight between 0 and 1 to the importance of each semantic unit. The higher the weight, the greater the contribution of the unit to the comprehensive semantic representation of the corresponding business attribute. The weighted average of the semantic units of the same business attribute can be used to obtain the comprehensive semantic vector of the attribute. The comprehensive semantic vectors of all business attributes are concatenated to form a 6000-dimensional vector, which is output as the result of the account period data analysis.

[0092] Specifically, the method of using the natural language processing model in the Copilot plug-in of Microsoft 365 to preprocess the text content of the account period data report and obtain the structured representation of the account period data report includes: according to the text content of the account period data report, using the natural language processing model in the Copilot plug-in of Microsoft 365 to preprocess the text content of the account period data report, obtain the features such as keywords, phrases and sentence structures in the account period data report, and obtain the structured representation of the account period data report by extracting and combining these features, and the structured representation includes the main content and key information of the account period data report. According to the structured representation of the account period data report, using the named entity recognition algorithm, the key entities such as the company name, date, amount, etc. that appear in the account period data report are identified and extracted, and the location and context information of these key entities in the account period data report are obtained. By analyzing the relationship between these key entities, important business information in the account period data report, such as the company's income, expenditure, profit and other financial indicators, is obtained.

[0093] Specifically, the vector representation of each semantic unit of the account period data report is obtained by performing semantic analysis on the structured representation, and the vector representation includes the semantic vector of each business attribute of the account period data report, including: according to the structured representation of the account period data report, the report content is segmented and part-of-speech tagged by natural language processing technology to obtain the semantic unit sequence of the report. By performing semantic role labeling on the semantic unit sequence, the key business attributes in the account period data report are identified, such as financial indicators such as operating income, net profit, and debt-to-asset ratio. A word vector model is used to vectorize each word in the semantic unit sequence to obtain a word vector sequence, and the word vector can characterize the semantic information of the word. According to the business attributes of the account period data report, the word vector sequence is weighted and aggregated using an attention mechanism to obtain a semantic vector representation of each business attribute, and the semantic vector can reflect the semantic characteristics of the business attribute.

[0094] Specifically, the similarity between the semantic units of the account period data report is calculated based on the cosine similarity algorithm to obtain a similarity matrix, including: according to the semantic units in the account period data report, each semantic unit is segmented by a word segmentation algorithm to obtain a keyword list for each semantic unit. By calculating the cosine similarity between the keyword lists of each semantic unit, the similarity values ​​between the semantic units are obtained. The similarity values ​​between the semantic units are constructed into a similarity matrix, and the similarity between the semantic units in the account period data report is determined to form a similarity matrix.

[0095] Specifically, based on the similarity matrix, a clustering algorithm is used to cluster the semantic units of the account period data report to obtain semantic clusters representing different business attributes, which specifically includes: according to the text content in the account period data report, the report is segmented and POS tagged using natural language processing technology to obtain the semantic units of the report. By calculating the similarity between semantic units, a semantic unit similarity matrix is ​​constructed to obtain the similarity relationship between semantic units. According to the similarity matrix, a hierarchical clustering algorithm is used to cluster the semantic units, and by setting a similarity threshold, semantic clusters representing different business attributes are obtained. For each semantic cluster, the business theme represented by the semantic cluster is determined according to the business attributes of the semantic units it contains, such as asset status, operating results, cash flow, etc.

[0096] Specifically, the business attribute label represented by each semantic cluster is obtained by performing keyword extraction and topic model analysis on the semantic units in each semantic cluster, including: according to the semantic units in each semantic cluster, using a keyword extraction algorithm to obtain the keywords of the semantic units; using a topic model analysis algorithm to divide the obtained keywords into topics to obtain the topics contained in each semantic cluster; according to the obtained semantic cluster topics, combined with a business attribute knowledge base, the business attribute label corresponding to each semantic cluster topic is determined; using a business attribute label evaluation algorithm to evaluate the obtained semantic cluster business attribute labels to obtain business attribute labels with high confidence; based on the obtained business attribute labels with high confidence, the final business attribute label represented by each semantic cluster is determined through business rule mapping.

[0097] Specifically, the business attribute label based on each semantic cluster and the vector representation of each semantic unit are weighted by using an attention mechanism to obtain a comprehensive semantic vector representation of each business attribute of the account period data report, including: obtaining the business attribute label corresponding to each semantic cluster according to the semantic clusters in the account period data report, such as financial indicators such as sales volume and profit margin. Using a word vector model, each semantic unit in the account period data report is vectorized to obtain a vector representation of the semantic unit. Through the attention mechanism, the correlation weight between each semantic unit and the business attribute label is calculated to obtain the importance weight of the semantic unit. According to the importance weight of the semantic unit, the vector representation of each semantic unit is weighted and summed to obtain a comprehensive semantic vector representation of each business attribute in the account period data report.

[0098] In some embodiments, the obtaining of the account period data analysis result further includes:

[0099] Based on the account period data analysis results, determine account period data of different risk levels;

[0100] The account period data of different risk levels are used as input features of the machine learning model, and a financial risk prediction model is generated by training the machine learning model;

[0101] The financial risk level of the new account period data is determined according to the financial risk prediction model.

[0102] In this embodiment, according to the account period data analysis results, the K-means clustering algorithm is used to divide the account period data of different risk levels. The specific steps include: through the account period data analysis, the risk score of each account period is obtained as the input feature vector of the clustering algorithm. The K-means clustering algorithm is used to divide the account period data into three categories: high risk, medium risk and low risk, where the K value is set to 3. During the clustering process, three account periods are randomly selected as the initial clustering centers, and the Euclidean distance between each account period data and the clustering center is calculated. According to the principle of the closest distance, each account period data is divided into the category where the corresponding clustering center is located, and the clustering center of each category is updated to the mean vector of all account period data under the category. Repeat the above process until the clustering center no longer changes or the maximum number of iterations is reached, and the final account period risk classification result is obtained. By analyzing the clustering results, it is determined that the risk level corresponding to the high-risk account period data is A, the risk level corresponding to the medium-risk account period data is B, and the risk level corresponding to the low-risk account period data is C. According to the account period risk level, the account period data sets under different risk levels are obtained, such as the A-level risk account period data set, the B-level risk account period data set and the C-level risk account period data set. Using statistical analysis methods, descriptive statistics are performed on key indicators such as the amount and overdue days of account period data of different risk levels to obtain the characteristic distribution of account period data of each risk level. By comparing and analyzing the differences in key indicators of account period data of different risk levels, the impact of account periods of different risk levels on the recovery of corporate funds can be judged, providing a basis for the subsequent formulation of targeted account period management strategies.

[0103] Next, the account period data of different risk levels are used as the input features of the machine learning model, and the data preprocessing technology is used to clean and standardize the account period data to obtain a high-quality training data set. The key features related to financial risk, such as the length of the account period, overdue situation, etc., are extracted from the account period data through feature engineering methods to obtain the optimized feature vector. Machine learning algorithms such as logistic regression, decision tree, support vector machine, etc. are used to input the feature vector into the model for training, and the optimal performance financial risk prediction model is obtained through parameter tuning. The real-time account period data of the enterprise to be predicted is obtained, and according to the previously obtained characteristic distribution of the account period data of each risk level, it is input into the trained machine learning model. The financial risk probability value of the enterprise is obtained through model prediction, and its risk level is judged according to the preset threshold to determine whether to grant credit and the credit limit. The financial risk prediction results are combined with other dimensional data of the enterprise, and a comprehensive evaluation method is used to obtain the overall credit score of the enterprise, providing a quantitative reference for credit decision-making.

[0104] S104, obtaining different categories of account period data analysis results by classifying the account period data analysis results, and distributing the different categories of account period data analysis results to corresponding staff members through preset personnel authority.

[0105] In this embodiment, different data access permissions are set for different staff members in the enterprise's information system (such as ERP, CRM, etc.), and these permissions are customized based on their responsibilities, roles, and business needs. The automation function of the enterprise information system is used to automatically distribute the different categories of account period data analysis results to the corresponding staff members, such as by setting up email notifications, system push, etc. Through the pre-set personnel authority distribution, it can be ensured that only staff members with corresponding permissions can access and view the account period data analysis results, thereby protecting the security and compliance of the data and helping to prevent data leakage and abuse.

[0106] In some embodiments, in the above step S104, the accounting period data analysis results are obtained by classifying the data, and the accounting period data analysis results of different categories are distributed to corresponding staff members through preset personnel authority, specifically including:

[0107] Determine the account period data features of the account period data analysis results, and use principal component analysis to perform dimensionality reduction processing on the account period data features to obtain the account period data features after dimensionality reduction;

[0108] The K-means clustering algorithm is used to perform cluster analysis on the account period data characteristics after dimension reduction to obtain the analysis results of account period data of different categories;

[0109] Based on the preset personnel authority information, access control list technology is used to determine the access rights of different categories of account period data analysis results;

[0110] Based on the access rights of different categories of account period data analysis results, determine the categories of account period data analysis results that different staff members can access;

[0111] Based on the authority information of each staff member, the analysis results of different categories of account period data are distributed to the corresponding staff members.

[0112] In this embodiment, the account period data features are obtained by analyzing the account period data, and the principal component analysis method is used to reduce the dimension of the account period data features to obtain the account period data features after dimension reduction. The account period data features after dimension reduction are used as the input of the K-means clustering algorithm, and the data points are divided into the categories corresponding to the nearest cluster center by calculating the distance from each data point to the cluster center, so as to obtain different categories of account period data analysis results. According to the preset personnel authority information, the access control list technology is used to determine the access rights of different categories of account period data analysis results. If a staff member has the access rights of the corresponding category of account period data analysis results, the account period data analysis results of this category are distributed to the staff member. The access rights of the account period data analysis results are controlled by the access control list technology, and the categories of account period data analysis results that different staff members can access are determined. According to the authority information of the staff member, the account period data analysis results of different categories are distributed to the corresponding staff member, so as to realize the effective management and distribution of the account period data analysis results.

[0113] For example, first determine the account period data characteristics including accounts receivable turnover rate, accounts receivable turnover days, accounts receivable to operating income ratio and other 10 indicators. Then, use principal component analysis to reduce the dimension of these 10 indicators. By calculating the eigenvalues ​​and eigenvectors, select the first three principal components, and the cumulative variance contribution rate reaches 85%, compressing the original data to three dimensions. Then, use the K-means clustering algorithm to cluster the account period data after dimensionality reduction, set the number of clusters k = 4, calculate the Euclidean distance between samples and iteratively update the cluster center, and finally divide the account period data into four categories. According to the preset personnel authority information, use the access control list technology to determine the access rights of different categories of account period data, such as the finance department can access all categories, and the sales department can only access the categories related to it. Based on the authority setting, determine the account period data categories that different staff members can access, such as the finance manager can access 4 categories of data, and the sales manager can only access 1 category of data. Finally, the system automatically sends the corresponding category of account period data analysis results to the corresponding personnel by email or push notification based on the authority information of each staff member, ensuring data security and efficient use.

[0114] Specifically, the account period data features of the account period data analysis results are determined, and the principal component analysis method is used to perform dimensionality reduction processing on the account period data features to obtain the account period data features after dimensionality reduction, including: according to the account period data analysis results, a data feature extraction method is used to obtain the feature vector of the account period data, including feature data of multiple dimensions such as the account period length, the transaction amount within the account period, and the transaction frequency. By normalizing the feature vector of the account period data, the feature data of different dimensions are unified to the same scale, and the dimensional influence between different features is eliminated. The principal component analysis method is used to perform feature dimensionality reduction on the normalized feature vector of the account period data, and by calculating the eigenvalues ​​and eigenvectors of the feature covariance matrix, the eigenvectors corresponding to the first k largest eigenvalues ​​are selected as the principal components to obtain the account period data features after dimensionality reduction.

[0115] Specifically, the K-means clustering algorithm is used to perform cluster analysis on the account period data features after dimension reduction to obtain the analysis results of account period data of different categories, including: using the K-means clustering algorithm to perform cluster analysis on the account period data features after dimension reduction, and randomly selecting K initial cluster center points as the starting point of the algorithm. The distance from each account period data point to each cluster center point is calculated according to the Euclidean distance, and each data point is divided into the category where the nearest cluster center point is located to form an initial clustering result. By calculating the mean of all data points in each cluster, the coordinates of the cluster center point are updated to obtain a new cluster center point. Using the new cluster center point, the clustering results are repeatedly executed and iteratively updated until the coordinates of the cluster center point no longer change significantly, and the clustering process is judged to converge, and the final account period data clustering results are obtained. According to the clustering results, the account period data in each cluster is statistically analyzed, and the statistical indicators such as the mean and variance of the account period data characteristics of each cluster are calculated to obtain the characteristic distribution of different categories of account period data. By comparing and analyzing the differences in the characteristic distribution of account period data of different clusters, combining business needs and expert knowledge, the business attributes of the account period data of each cluster are interpreted and labeled to obtain account period data classification results with business significance.

[0116] Specifically, the access rights of different categories of account period data analysis results are determined by using access control list technology according to preset personnel authority information, including: establishing an access right matrix of account period data analysis results according to preset personnel authority information, and mapping different categories of account period data analysis results with corresponding personnel authority. Obtain the identity information of the current user, verify the legitimacy of the user identity through the identity authentication system, and obtain the authority group to which the user belongs. According to the authority group to which the user belongs, find the corresponding account period data analysis result access right in the access right matrix, and determine the user's access level to different categories of account period data analysis results. When the user requests to access a specific category of account period data analysis results, obtain the requested account period data category, and find the access control rule corresponding to the category in the access right matrix. According to the access control rule, determine whether the user has the authority to access the requested account period data analysis results. If the user has the corresponding access right, the user is allowed to access and return the requested data analysis results; otherwise, the user's access request is rejected, and a prompt message indicating that the access is denied is returned. In the access control process, the user's access log is recorded, including information such as access time, accessed data category, and access result, so as to facilitate auditing and tracking. At the same time, the sensitive account period data analysis results are desensitized to ensure data security. The access control list is reviewed and updated regularly, and the access permission matrix is ​​modified in a timely manner according to changes in business needs and adjustments to personnel permissions to ensure the effectiveness and accuracy of the access control strategy. At the same time, the access control system is reinforced to prevent unauthorized access and data leakage.

[0117] Specifically, the access rights based on different categories of account period data analysis results determine the categories of account period data analysis results accessible to different staff members, including: obtaining a permission list of account period data analysis result categories accessible to different staff members according to their job responsibilities and departments; using a permission mapping table to match the permission categories in the permission list with the categories of account period data analysis results to obtain a mapping relationship between the account period data analysis result categories accessible to each staff member; obtaining a list of account period data analysis result categories accessible to each staff member by traversing the mapping relationship of each staff member; according to the list of account period data analysis results categories, using a database query statement to obtain analysis result data of corresponding categories from the account period data analysis result table; associating the analysis result data obtained by the query with the information of the staff member to generate the account period data analysis results accessible to the staff member. view; through the user authentication and authorization mechanism, determine the identity of the staff member who is currently accessing the account period data analysis results, and obtain the corresponding account period data analysis result view; according to the staff member's request, obtain the required analysis result data from the corresponding account period data analysis result view, and return it to the staff member; through the log recording function, record the time, content and operation type of each staff member's access to the account period data analysis results, so as to conduct data access audit and tracking; based on the data access log, use the data analysis algorithm to regularly analyze the data access behavior of the staff, identify suspicious access patterns and abnormal behaviors, and determine whether there is a risk of data leakage or abuse; according to the results of the data access behavior analysis, dynamically adjust the data access rights of the staff, warn and restrict high-risk access behaviors, and ensure the security and compliance of the account period data analysis results.

[0118] Reference Figure 2 An embodiment of the present invention provides a billing period data processing system 2 based on Microsoft 365, wherein the system 2 specifically includes:

[0119] The first processing module 201 is used to obtain account period data based on the data interface of the financial data management system, and import the account period data into an Excel file according to a preset data mapping rule, wherein the account period data includes management reporting data and legal reporting data;

[0120] The second processing module 202 is used to perform data cleaning and data conversion on the account period data in multiple Excel files based on the Power Query function of Microsoft 365, and then build an account period data model according to the association relationship between the account period data in the multiple Excel files;

[0121] The third processing module 203 is used to obtain an account period data report after data visualization of the account period data model, and to perform intelligent analysis on the account period data report using the Copilot plug-in of Microsoft 365 to obtain an account period data analysis result;

[0122] The fourth processing module 204 is used to obtain different types of account period data analysis results by classifying the account period data analysis results, and distribute the different types of account period data analysis results to corresponding staff members according to preset personnel permissions.

[0123] It is understandable that if Figure 1 The contents of the embodiment of the method for processing account period data based on Microsoft 365 shown in the figure are applicable to the embodiment of the system for processing account period data based on Microsoft 365. The functions specifically implemented by the embodiment of the system for processing account period data based on Microsoft 365 are the same as those in the embodiment of the method for processing account period data based on Microsoft 365. Figure 1 The embodiment of the method for processing account period data based on Microsoft 365 shown in FIG. 1 is the same as that shown in FIG. 1 , and the beneficial effects achieved are the same as those of FIG. Figure 1 The beneficial effects achieved by the embodiment of the billing period data processing method based on Microsoft 365 shown are also the same.

[0124] It should be noted that the information interaction, execution process and other contents between the above-mentioned systems are based on the same concept as the embodiment of the method of the present invention. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0125] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0126] Reference Figure 3The embodiment of the present invention further provides a computer device 3, comprising: a memory 302 and a processor 301 and a computer program 303 stored in the memory 302. When the computer program 303 is executed on the processor 301, the account period data processing method based on Microsoft 365 as described in any one of the above methods is implemented.

[0127] The computer device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will appreciate that Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0128] The processor 301 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0129] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may also be an external storage device of the computer device 3, 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 (Flash Card), etc. equipped on the computer device 3. Further, the memory 302 may also include both an internal storage unit of the computer device 3 and an external storage device. The memory 302 is used to store an operating system, an application program, a boot loader (Boot Loader), data, and other programs, such as the program code of the computer program, etc. The memory 302 may also be used to temporarily store data that has been output or is to be output.

[0130] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for processing account period data based on Microsoft 365 as described in any one of the above methods is implemented.

[0131] In this embodiment, if the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0132] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0133] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0134] In the embodiments disclosed in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Claims

1. A method for processing account period data based on Microsoft 365, characterized in that: The method specifically comprises: Based on the data interface of the financial data management system, the account period data is obtained, and the account period data is imported into the Excel file through the preset data mapping rules, wherein the account period data includes the management report data and the legal report data; After cleaning and converting the account period data in multiple Excel files based on the Power Query function of Microsoft 365, a account period data model is constructed based on the association between the account period data in multiple Excel files; After data visualization of the account period data model, an account period data report is obtained, and the account period data report is intelligently analyzed using the Copilot plug-in of Microsoft 365 to obtain an account period data analysis result; The method of using the Microsoft 365 Copilot plug-in to intelligently analyze the account period data report to obtain the account period data analysis results specifically includes: Using a natural language processing model in the Copilot plug-in of Microsoft 365, preprocessing the text content of the account period data report is performed to obtain a structured representation of the account period data report; By performing semantic analysis on the structured representation, a vector representation of each semantic unit of the account period data report is obtained, wherein the vector representation includes a semantic vector of each business attribute of the account period data report; Based on the cosine similarity algorithm, the similarity between the semantic units of the account period data report is calculated to obtain a similarity matrix; Based on the similarity matrix, a clustering algorithm is used to cluster the semantic units of the account period data report to obtain semantic clusters representing different business attributes; By performing keyword extraction and topic model analysis on the semantic units in each semantic cluster, the business attribute label represented by each semantic cluster is obtained; Based on the business attribute label of each semantic cluster and the vector representation of each semantic unit, an attention mechanism is used to weight the importance of each semantic unit to obtain a comprehensive semantic vector representation of each business attribute of the account period data report; Obtaining an account period data analysis result by splicing the comprehensive semantic vectors of each business attribute of the account period data report; The account period data analysis results are classified into different categories through data classification, and the account period data analysis results of different categories are distributed to corresponding staff members through preset personnel authority.

2. The method according to claim 1, characterized in that The importing of the account period data into the Excel file according to the preset data mapping rules specifically includes: Using regular expressions to verify and clean the data format of the account period data in the Excel file to obtain standardized account period data; Analyze the standardized account period data according to an association rule mining algorithm to obtain the association relationship of the standardized account period data and form a data chain; Based on the data chain, a graph neural network model is used to extract features of the standardized account period data to obtain a data feature vector; Using a support vector machine model to process the data feature vector, determine abnormal data or incomplete data in the standardized account period data, and perform data repair on the abnormal data or incomplete data in the standardized account period data; Based on data types and business rules, the standardized account period data after data repair is classified according to the decision tree model and mapped to the specified location in the Excel file; The standardized account period data in the Excel file is verified according to the convolutional neural network, and a data quality report is generated through feature matching and similarity calculation.

3. The method according to claim 1, characterized in that: The constructing of the account period data model according to the association relationship between the account period data in the multiple Excel files specifically includes: By analyzing the association between the account period data in multiple Excel files, a fact table and a dimension table are determined, wherein the fact table includes the measurement values ​​of the account period data, and the plurality of dimension tables include the dimension attributes of the account period data; Establish the association between the fact table and the dimension table through the primary key and foreign key to form the first account period data model; mining association rules between the account period data in the first account period data model according to an association rule mining algorithm to obtain a second account period data model; Using data cube technology to perform multi-dimensional analysis on the second account period data model to obtain a third account period data model; The account period data in the third account period data model is predicted and analyzed according to a time series analysis algorithm to obtain a target account period data model.

4. The method according to claim 3, characterized in that The mining of association rules between the account period data in the first account period data model according to the association rule mining algorithm specifically includes: Acquire multiple account period attributes of the account period data in the first account period data model to form an initial data set; Obtaining a first frequent itemset by counting the support of each account period attribute in the initial data set, wherein the first frequent itemset is a set of account period attributes whose support is greater than or equal to a minimum support threshold; Generate a candidate payment period attribute pair by connecting every two payment period attributes in the first frequent item set; By counting the support of each candidate account period attribute pair, a second frequent item set is obtained, where the second frequent item set is a set of candidate account period attribute pairs whose support is greater than or equal to a minimum support threshold; Repeat the steps of generating the candidate account period attribute pairs and generating the second frequent item set until no higher-order frequent item sets can be generated, thereby obtaining a kth frequent item set; The confidence of each frequent item set in the kth frequent item set is calculated to obtain an association rule, where the association rule is an implied relationship between frequent item sets whose confidence is greater than or equal to a minimum confidence threshold.

5. The method according to claim 1, characterized in that The obtaining of the account period data analysis result further includes: Based on the account period data analysis results, determine account period data of different risk levels; The account period data of different risk levels are used as input features of the machine learning model, and a financial risk prediction model is generated by training the machine learning model; The financial risk level of the new account period data is determined according to the financial risk prediction model.

6. The method according to claim 1, characterized in that The method of obtaining different types of account period data analysis results by classifying the account period data analysis results, and distributing the different types of account period data analysis results to corresponding staff members through preset personnel authority, specifically includes: Determine the account period data features of the account period data analysis results, and use principal component analysis to perform dimensionality reduction processing on the account period data features to obtain the account period data features after dimensionality reduction; The K-means clustering algorithm is used to perform cluster analysis on the account period data characteristics after dimension reduction to obtain the analysis results of account period data of different categories; Based on the preset personnel authority information, access control list technology is used to determine the access rights of different categories of account period data analysis results; Based on the access rights of different categories of account period data analysis results, determine the categories of account period data analysis results that different staff members can access; Based on the authority information of each staff member, the analysis results of different categories of account period data are distributed to the corresponding staff members.

7. A billing period data processing system based on Microsoft 365, characterized in that: The system specifically comprises: A first processing module is used to obtain account period data based on a data interface of a financial data management system, and import the account period data into an Excel file according to a preset data mapping rule, wherein the account period data includes management reporting data and legal reporting data; The second processing module is used to clean and convert the account period data in multiple Excel files based on the Power Query function of Microsoft 365, and then build an account period data model according to the correlation between the account period data in multiple Excel files; A third processing module is used to obtain an account period data report after data visualization of the account period data model, and to perform intelligent analysis on the account period data report using the Copilot plug-in of Microsoft 365 to obtain an account period data analysis result; The method of using the Microsoft 365 Copilot plug-in to intelligently analyze the account period data report to obtain the account period data analysis results specifically includes: Using a natural language processing model in the Copilot plug-in of Microsoft 365, preprocessing the text content of the account period data report is performed to obtain a structured representation of the account period data report; By performing semantic analysis on the structured representation, a vector representation of each semantic unit of the account period data report is obtained, wherein the vector representation includes a semantic vector of each business attribute of the account period data report; Based on the cosine similarity algorithm, the similarity between the semantic units of the account period data report is calculated to obtain a similarity matrix; Based on the similarity matrix, a clustering algorithm is used to cluster the semantic units of the account period data report to obtain semantic clusters representing different business attributes; By performing keyword extraction and topic model analysis on the semantic units in each semantic cluster, the business attribute label represented by each semantic cluster is obtained; Based on the business attribute label of each semantic cluster and the vector representation of each semantic unit, an attention mechanism is used to weight the importance of each semantic unit to obtain a comprehensive semantic vector representation of each business attribute of the account period data report; Obtaining an account period data analysis result by splicing the comprehensive semantic vectors of each business attribute of the account period data report; The fourth processing module is used to obtain different categories of account period data analysis results by classifying the account period data analysis results, and distribute the different categories of account period data analysis results to corresponding staff members through preset personnel permissions.

8. A computer device, characterized in that: include: A memory and a processor and a computer program stored in the memory, when the computer program is executed on the processor, implements the account period data processing method based on Microsoft 365 as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method for processing account period data based on Microsoft 365 as described in any one of claims 1 to 6 is implemented.

Images