Enterprise financial data information management system and method

Abstract

The invention relates to the technical field of information management, and discloses an enterprise financial data information management system and method, and the method comprises the steps: obtaining enterprise financial data, carrying out the data analysis of the financial data, obtaining structured data, carrying out the intelligent classification of the structured data, and obtaining classified data; performing trend analysis on the classified data to obtain a financial trend, performing anomaly analysis on the classified data by utilizing the financial trend to obtain an anomaly result, and generating a financial analysis report according to the anomaly result, the classified data and the financial trend; performing compliance check on the analysis report to obtain a compliance result; and constructing a distributed account book according to the compliance result and the analysis report. The problem that an existing enterprise financial data information management method is not high in management efficiency can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of information management, and in particular to an enterprise financial data information management system and method. Background Art

[0002] In the current daily operation and management of enterprises, financial data information management plays a vital role as the core link of enterprise decision-making and operation. It not only directly affects the key business activities of enterprises such as capital flow, cost control, profit distribution, but also provides a basis for management to formulate strategic planning, optimize resource allocation, evaluate performance and manage risks.

[0003] However, traditional enterprise financial management systems are usually isolated, and the financial data between departments lack effective integration. For example, the revenue data of the sales department, the cost data of the procurement department, and the salary data of the human resources department are scattered in different systems, and seamless connection cannot be achieved. This not only increases the difficulty of data integration, but may also lead to information asymmetry, affect cross-departmental collaboration and the accuracy of overall decision-making. In addition, the financial environment of modern enterprises is becoming increasingly complex, and traditional financial software has difficulty processing such large and complex data sets. For example, an enterprise may need to simultaneously analyze sales revenue in different regions, profit margins of different products, and lifetime values ​​of different customers, but traditional tools often cannot provide sufficient flexibility and depth. In summary, the existing enterprise financial data information management method still has the problem of low management efficiency. Summary of the invention

[0004] The present invention provides an enterprise financial data information management system, the main purpose of which is to solve the problem of low management efficiency of an existing enterprise financial data information management method.

[0005] To achieve the above object, the present invention provides a method for managing enterprise financial data information, the method comprising: Acquire enterprise financial data, perform data analysis on the financial data to obtain structured data, and intelligently classify the structured data to obtain classified data; Performing trend analysis on the classified data to obtain financial trends, performing anomaly analysis on the classified data using the financial trends to obtain anomaly results, and generating a financial analysis report based on the anomaly results, the classified data, and the financial trends; Performing compliance check on the analysis report to obtain compliance results; A distributed ledger is constructed according to the compliance results and the analysis report.

[0006] Optionally, the performing data parsing on the financial data to obtain structured data includes: Performing entity recognition on the financial data to obtain named entities; Performing semantic analysis on the financial data according to the named entities to obtain data semantics; extracting key data from the financial data using the field semantics; Performing data standardization on the key data to obtain standardized data; The standardized data is structured and stored to obtain structured data.

[0007] Optionally, the intelligently classifying the structured data to obtain classified data includes: Performing outlier processing on the structured data to obtain preprocessed data; Performing feature extraction on the preprocessed data to obtain feature data; Performing feature standardization on the clustering features of the feature data to obtain clustering features; The pre-processed data is clustered using the clustering features to obtain classified data.

[0008] Optionally, performing trend analysis on the classified data to obtain financial trends includes: sorting the classified data in time to obtain a time series; Calculate the trend indicator of the time series; Performing moving average on the time series to obtain smoothed data; Performing trend line fitting on the smoothed data to obtain a trend line graph; A financial trend is generated according to the trend line graph and the trend indicator.

[0009] Optionally, performing an abnormal analysis on the classified data using the financial trend to obtain an abnormal result includes: Constructing a trend-guiding feature matrix according to the financial trend and the classification data; Randomly selecting a feature from the trend-guiding feature matrix as a feature to be processed; The trend-guiding feature matrix is ​​divided according to the feature to be processed to obtain a left subset and a right subset; Repeating the segmentation of the left subset and the right subset to obtain an isolated data set; constructing an isolation tree according to the isolation data set; Counting the path length of each data point of the isolated tree species; Calculating an isolation score for each data point in the isolation tree according to the path length; Abnormal results are screened out from the classified data according to the isolation score.

[0010] Optionally, generating a financial analysis report according to the abnormal result, the classification data and the financial trend includes: Perform correlation analysis based on the abnormal results and the financial trends to obtain correlation results; Perform abnormal classification analysis according to the abnormal result, the correlation result and the classification data to obtain the abnormal cause; Summarize the data according to the abnormal results and the abnormal reasons to obtain an abnormal summary; Fill in the template according to the financial trend to obtain an overview of the financial trend; The abnormal point summary and the financial trend overview are framed to obtain a financial analysis report.

[0011] Optionally, performing a compliance check on the analysis report to obtain a compliance result includes: Comparing the analysis report with the financial data for data consistency to obtain a comparison result; Performing a sensitive information test on the analysis report to obtain a sensitivity result; The analysis report is scored for compliance according to the sensitivity result and the comparison result to obtain a compliance result.

[0012] Optionally, constructing a distributed ledger according to the compliance result and the analysis report includes: Constructing a transaction record from the compliance result and the analysis report; Packing the transaction records into blocks to obtain block package data; Calculating the hash value of the block packet; Linking the block package data to a preset blockchain according to the hash value to obtain a blockchain account book; The blockchain ledger is synchronized in a distributed manner to obtain a distributed ledger.

[0013] Optionally, calculating the hash value of the block packet includes: Serializing the block packet into binary data; Performing byte padding on the binary data to obtain padding data; Blocking the filling data to obtain block data; A cyclic operation is performed on the block data to obtain a hash value.

[0014] In order to solve the above problems, the present invention also provides an enterprise financial data information management system, the system includes a classification module, a reporting module, a checking module and a building module, specifically: Classification module: used to obtain enterprise financial data, perform data analysis on the financial data to obtain structured data, and perform intelligent classification on the structured data to obtain classified data; A reporting module, configured to perform trend analysis on the classified data to obtain financial trends, perform abnormality analysis on the classified data using the financial trends to obtain abnormal results, and generate a financial analysis report based on the abnormal results, the classified data, and the financial trends; A checking module, used for performing a compliance check on the analysis report to obtain a compliance result; A construction module is used to construct a distributed ledger according to the compliance results and the analysis report.

[0015] The present invention uses time series analysis to track the changing trends of key indicators such as income, cost, and cash flow in real time, so that management can quickly grasp the financial health status and improve the real-time and efficiency of decision-making; by performing preliminary data processing on local devices, the delay of data transmission is reduced, and then the processed data is constructed into a distributed ledger technology (such as blockchain) to achieve transparency and immutability of financial data and simplify data storage and management processes. Therefore, the enterprise financial data information management method proposed by the present invention can solve the problem of low management efficiency of existing enterprise financial data information management methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a method for managing enterprise financial data information provided by one embodiment of the present invention; Figure 2 A schematic diagram of a data analysis process according to an embodiment of the present invention; Figure 3 A schematic diagram of a trend analysis process provided by an embodiment of the present invention; Figure 4 A functional module diagram of an enterprise financial data information management system provided by one embodiment of the present invention.

[0017] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0019] The embodiment of the present application provides a method for managing enterprise financial data information. The execution subject of the enterprise financial data information management method includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the enterprise financial data information management method can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0020] Reference Figure 1 FIG. 1 is a flow chart of a method for managing enterprise financial data information provided by an embodiment of the present invention. In this embodiment, a method for managing enterprise financial data information includes: S1. Acquire enterprise financial data, perform data analysis on the financial data to obtain structured data, and intelligently classify the structured data to obtain classified data.

[0021] In an embodiment of the present invention, unstructured data (such as contracts, invoices, receipts) are automatically parsed into structured data, reducing the time and errors of manual sorting, and can quickly integrate data from multiple sources (ERP systems, bank statements, paper documents, etc.), thereby improving data processing efficiency.

[0022] In an embodiment of the present invention, the enterprise financial data refers to various quantitative information (such as contracts, invoices, receipts) related to the financial status, operating results and cash flow generated by the enterprise during its business operations, and converts financial documents in different formats (such as PDF, pictures, Excel) into a parsable text format.

[0023] Ginseng Figure 2 As shown, in the embodiment of the present invention, the data parsing of the financial data to obtain structured data includes: S21, performing entity recognition on the financial data to obtain named entities; S22, performing semantic analysis on the financial data according to the named entities to obtain data semantics; S23, extracting key data from the financial data using the field semantics; S24, performing data standardization on the key data to obtain standardized data; S25. Perform structured storage on the standardized data to obtain structured data.

[0024] In an embodiment of the present invention, entity recognition is to identify and classify specific entities from text, such as dates, amounts, organization names, transaction records, etc. First, the financial data is decomposed into words or phrases to obtain word segmentation data, and then the text is annotated using a natural language processing model (such as a NER model) or a rule matching method, and finally a named entity with a label is obtained, such as "operating cost": "3 million yuan", "net profit": "2 million yuan", etc.

[0025] In the embodiment of the present invention, the relationship between entities is obtained by contextual analysis of the named entities. For example, based on financial logic, it is clear that "income" minus "operating costs" equals "net profit", and the obtained relationship is compared with the preset standardized chart of accounts to confirm that its semantics belongs to the financial category. Finally, the logic between data is identified using the financial knowledge graph or business rules. For example, it is determined that the unit of money "10,000 yuan" needs to be converted into the standard currency unit.

[0026] In the embodiment of the present invention, key data including financial data and time fields are extracted from the financial data according to the data semantics.

[0027] In an embodiment of the present invention, the key data is standardized in numerical units, time formats and field names, the numerical units and time formats are converted into a unified time format, the field names with the same meanings are merged according to corresponding semantic interpretations, and the names are unified and standardized.

[0028] In the embodiment of the present invention, storing the standardized data in a structured format refers to storing the standardized data in a relational database and establishing an index relationship to obtain structured data.

[0029] In the embodiment of the present invention, the intelligent classification of the structured data to obtain the classified data includes: Performing outlier processing on the structured data to obtain preprocessed data; Performing feature extraction on the preprocessed data to obtain feature data; Performing feature standardization on the clustering features of the feature data to obtain clustering features; The pre-processed data is clustered using the clustering features to obtain classified data.

[0030] In an embodiment of the present invention, the outlier processing refers to using preset business rules to filter outliers from the structured data. For example, the revenue value of a product cannot be negative. The filtered results are deleted and a marker field is added at the data position to obtain preprocessed data.

[0031] In the embodiment of the present invention, the feature extraction refers to the consolidation of financial accounts. For example: EBITDA (earnings before interest, taxes, depreciation and amortization) = operating income - operating costs - management expenses. The time or category field is encoded (such as converting the date into days, or converting the category into a one-hot encoding), and each record corresponds to a set of feature data, including the generated feature value.

[0032] In the embodiment of the present invention, the characteristic value is scaled to the interval [0, 1] by a minimum-maximum normalization algorithm to obtain a clustering feature.

[0033] In the embodiment of the present invention, the number of clustering classes of the clustering feature is evaluated by the elbow rule or the silhouette coefficient, and the clustering feature is clustered using a clustering algorithm (such as the k-means algorithm), and a label for each data is generated to obtain classified data.

[0034] In the embodiment of the present invention, by automatically classifying data, the speed of data processing is accelerated, the management risk of relying on manual operations is reduced, the enterprise's ability to instantly grasp multi-dimensional financial information is improved, and the management response speed is improved.

[0035] S2. Perform trend analysis on the classified data to obtain financial trends, perform anomaly analysis on the classified data using the financial trends to obtain abnormal results, and generate a financial analysis report based on the abnormal results, the classified data, and the financial trends.

[0036] In the embodiment of the present invention, time series analysis is used to track the changing trends of key indicators such as income, cost, cash flow, etc. in real time, providing dynamic visualization of financial data to help enterprises understand the changing direction of financial status in a timely manner. Dynamic trend analysis supports management to quickly grasp the financial health status and improve the real-time and efficiency of decision-making.

[0037] Ginseng Figure 3 As shown, in the embodiment of the present invention, the trend analysis of the classified data to obtain the financial trend includes: S31, sorting the classified data by time to obtain a time series; S32, calculating the trend index of the time series; S33, performing moving average on the time series to obtain smoothed data; S34, performing trend line fitting on the smoothed data to obtain a trend line graph; S35. Generate a financial trend according to the trend line graph and the trend indicator.

[0038] In the embodiment of the present invention, the classified data are arranged in chronological order to form a time series, and the time fields corresponding to the classified data are extracted and the data are arranged in ascending order according to the time fields to finally form a continuous time series.

[0039] In an embodiment of the present invention, core trend indicators are extracted from the time series to describe the dynamic characteristics of data changing over time. The trend indicators include: calculating the percentage change between adjacent time points, calculating the cumulative change from the start time to the current time point, and calculating the change amplitude or standard deviation of the indicator to reflect the stability of the time series.

[0040] In an embodiment of the present invention, the average value of adjacent time points is taken for each point in the time series through a preset time window, and the average value is used to replace the data corresponding to the time window to obtain smooth data. When the starting point or the end point is less than the window size, a moving average can be performed through a data filling method (such as repeated value or zero value filling).

[0041] In an embodiment of the present invention, the trend line fitting is to find a trend line that best represents the overall change trend through a fitting method, use the time point of the smoothed data as the independent variable, and the corresponding financial indicator (such as net profit) as the dependent variable, calculate the coefficient of the fitting function, generate a trend line formula, and plot the actual data of the time series, the smoothed data and the fitted trend line in the graph at the same time to obtain a trend line graph.

[0042] In the embodiment of the present invention, the financial trend is to generate insights into future financial trends by combining the analysis of trend line graphs and trend indicators, describe the current financial performance through calculations based on trend indicators, predict financial indicators at future time points based on trend line formulas, determine growth or decline trends, and point out potential risks or opportunities, i.e., trend recommendations. Financial indicators, financial performance, trend line graphs, trend lines, and trend recommendations are aggregated to obtain financial trends.

[0043] In the embodiment of the present invention, the use of the financial trend to perform an abnormal analysis on the classified data to obtain an abnormal result includes: Constructing a trend-guiding feature matrix according to the financial trend and the classification data; Randomly selecting a feature from the trend-guiding feature matrix as a feature to be processed; The trend-guiding feature matrix is ​​divided according to the feature to be processed to obtain a left subset and a right subset; Repeating the segmentation of the left subset and the right subset to obtain an isolated data set; constructing an isolation tree according to the isolation data set; Counting the path length of each data point of the isolated tree species; Calculating an isolation score for each data point in the isolation tree according to the path length; Abnormal results are screened out from the classified data according to the isolation score.

[0044] In an embodiment of the present invention, the expected value of each time point is calculated based on the trend line in the financial trend, the deviation between the classified data and the trend value is calculated to obtain the deviation value, data splicing is performed based on the classified data, the deviation value and the trend indicator in the financial trend to obtain the guiding feature, and all the guiding features are arranged to obtain a guiding feature matrix.

[0045] In the embodiment of the present invention, during the process of constructing the isolation tree, one feature is randomly selected each time as the basis for segmentation. For example, if the feature matrix contains three features (net profit, growth rate, volatility), the second column (growth rate) may be randomly selected in this step.

[0046] In the embodiment of the present invention, the feature matrix is ​​divided into two parts by randomly selecting features and their segmentation thresholds, and a threshold is randomly selected within the value range of the feature to be processed, for example, the range of "growth rate" is [0.2, 0.25], and the randomly selected segmentation point is 0.22. Using the selected segmentation threshold, the feature matrix is ​​divided into a left subset and a right subset: left subset: feature value to be processed <0.22; right subset: feature value to be processed ≥ 0.22.

[0047] In the embodiment of the present invention, a feature is randomly selected again for each subset as a segmentation basis, a segmentation threshold is randomly selected and the subset is further segmented, and the above steps are repeated until the number of data points in each subset is 1 or the segmentation depth reaches a preset maximum value.

[0048] In an embodiment of the present invention, an isolation tree is constructed using segmentation rules. Each node in the isolation tree stores randomly selected features, segmentation thresholds, and links to child nodes. The node content can be expressed as: feature: growth rate, segmentation point: 0.22, child nodes: left and right subsets.

[0049] In the embodiment of the present invention, the following formula can be used to calculate the isolation score: in, For data points The isolated fraction of For data points The average isolation path length, is the normalized path length, which represents the average number of splits in the tree.

[0050] In the embodiment of the present invention, based on a preset threshold, data points whose isolation scores are greater than the threshold are marked as abnormal, and abnormal data corresponding to the isolated score points are screened out from the classified data.

[0051] In the embodiment of the present invention, generating a financial analysis report according to the abnormal result, the classification data and the financial trend includes: Perform correlation analysis based on the abnormal results and the financial trends to obtain correlation results; Perform abnormal classification analysis according to the abnormal result, the correlation result and the classification data to obtain the abnormal cause; Summarize the data according to the abnormal results and the abnormal reasons to obtain an abnormal summary; Fill in the template according to the financial trend to obtain an overview of the financial trend; The abnormal point summary and the financial trend overview are framed to obtain a financial analysis report.

[0052] In an embodiment of the present invention, by analyzing the difference between abnormal data points and trend data, statistical or machine learning methods are used to mine hidden associations, such as whether the abnormal points appear near the trend turning point, or whether they are related to significant deviations from a specific financial indicator.

[0053] In the embodiment of the present invention, the abnormal result process is classified into different abnormal types according to the nature and isolation score of the abnormal point, and then the classified abnormal data is used to extract additional information from the classified data, and the specific indicator association of the abnormality is further identified using a regression or classification model. For example, revenue-related anomalies: if the net profit is significantly higher than the trend, it may be related to one-time income or non-recurring gains and losses; cost-related anomalies: if the operating cost increases or decreases abnormally, it may be related to sudden costs (raw material fluctuations, etc.); data error anomalies: may come from input errors or missing values.

[0054] In the embodiment of the present invention, all abnormal results are summarized, including abnormal date, isolation score, classification type, correlation trend, etc., the abnormal causes are grouped and counted by type, the commonalities and key points of the abnormal occurrence are extracted, and finally an abnormal summary is formed, such as {"total number of abnormal points": 5, "distribution of abnormal types": {"revenue related": "70%", "cost related": "30%"}, "abnormal commonality summary": "mainly concentrated in the months with high net profit volatility, and related to one-time income"}.

[0055] In the embodiment of the present invention, trend data is used to generate a chart, and the chart and data extracted from the financial trend are filled into a preset trend template. For example: Net profit trend: It continued to rise from January to March, with an average monthly growth rate of 20%. Operating income trend: Revenue had an inflection point in February, and increased by 10% month-on-month in March.

[0056] In an embodiment of the present invention, an outlier summary and a financial trend overview are integrated to generate a complete financial analysis report according to a predefined framework, which can unify the report content and format, improve the standardization level of financial management work, improve the efficiency of financial report generation, provide management with visual and easy-to-understand analysis reports, and improve decision-making efficiency.

[0057] In the embodiment of the present invention, a financial analysis report is automatically generated, integrating trend analysis and anomaly detection results.

[0058] S3. Perform a compliance check on the analysis report to obtain a compliance result.

[0059] In the embodiment of the present invention, automated compliance checking verifies the accuracy, legality and compliance of data (such as whether it complies with accounting standards, tax regulations, etc.) through a rule engine, promptly discovers and marks non-compliance in financial data, and avoids subsequent audit issues.

[0060] In the embodiment of the present invention, the compliance check of the analysis report to obtain the compliance result includes: Comparing the analysis report with the financial data for data consistency to obtain a comparison result; Performing a sensitive information test on the analysis report to obtain a sensitivity result; The analysis report is scored for compliance according to the sensitivity result and the comparison result to obtain a compliance result.

[0061] In an embodiment of the present invention, key financial indicators are extracted from the analysis report, corresponding data of the same period are extracted from financial data (such as a database or original data file) for comparison, the report data and the financial data are compared, the error or deviation rate is calculated, and the deviation rate is used as the comparison result.

[0062] In the embodiment of the present invention, the sensitive information check refers to identifying whether the report contains sensitive information, such as private data, commercial secrets, or information prohibited from disclosure by laws and regulations, to ensure that the content of the report complies with regulatory requirements. By using the preset sensitive information type, the sensitive information type is searched in the analysis report (a fuzzy matching algorithm or a whole expression can be used), the detected sensitive information is marked, and a sensitivity result is generated, indicating whether sensitive information is contained and the type and location of the sensitive information.

[0063] In the embodiments of the present invention, automated compliance checking can significantly reduce the time of manual checking, improve the efficiency of compliance review, provide an automated compliance feedback process, and make the management process smoother and more efficient.

[0064] S4. Construct a distributed ledger based on the compliance results and the analysis report.

[0065] In the embodiment of the present invention, by providing distributed storage and sharing capabilities, the transparency and immutability of financial data are achieved, the data storage and management process is simplified, and the difficulty of data management during cross-departmental collaboration is reduced.

[0066] In an embodiment of the present invention, the step of constructing a distributed ledger according to the compliance result and the analysis report includes: Constructing a transaction record from the compliance result and the analysis report; Packing the transaction records into blocks to obtain block package data; Calculating the hash value of the block packet; Linking the block package data to a preset blockchain according to the hash value to obtain a blockchain account book; The blockchain ledger is synchronized in a distributed manner to obtain a distributed ledger.

[0067] In the embodiment of the present invention, the compliance result and the analysis report are organized into a standardized structure (such as JSON or other formats) as a carrier of transaction records.

[0068] In an embodiment of the present invention, all transaction records generated in the current cycle (such as all analysis reports after compliance checks) are collected, and block header information is added, including block number, timestamp, previous block hash (prev_hash), etc., to obtain a block package.

[0069] In the embodiment of the present invention, the step of calculating the hash value of the block packet includes: Serializing the block packet into binary data; Performing byte padding on the binary data to obtain padding data; Blocking the filling data to obtain block data; A cyclic operation is performed on the block data to obtain a hash value.

[0070] In detail, the serialization refers to converting the block package into a JSON format string, removing unnecessary spaces to obtain a string, and performing UTF-8 byte encoding on the string to obtain binary data.

[0071] Specifically, pad the input byte stream so that its length becomes an integer multiple of 512 bits.

[0072] In detail, the padded data is divided into multiple 512-bit blocks, each block is processed independently, and the initial state value is fixed to 8 32-bit constants (256 bits in total).

[0073] In detail, each block is processed through 64 rounds of iterations and merged into the state value by accumulation using logical operations (e.g., bitwise operations, shifts) and a fixed constant table. After all blocks are processed, the final state value is output as a hash value.

[0074] In the embodiment of the present invention, in the blockchain, the hash value of the current block package is recorded as the hash of the latest block in the chain and linked to the hash of the previous block (prev_hash). By checking whether the "previous block hash" of each block is consistent with the hash value of the previous block, the integrity of the chain is ensured, and finally an updated blockchain account book is obtained.

[0075] In the embodiment of the present invention, by identifying all nodes of the blockchain ledger, each node checks whether its own ledger is in the latest state. If it is inconsistent, the latest block is pulled from other nodes. If multiple versions of the blockchain are found, the longest chain rule is used to select the legal chain, and the synchronized blockchain ledger is stored in the local storage of each node to form a distributed ledger.

[0076] In the embodiments of the present invention, distributed ledger technology is used to improve data storage and access efficiency, reduce management lag problems caused by information islands, provide real-time data sharing and update capabilities, reduce information synchronization time, and improve management collaboration efficiency.

[0077] like Figure 4 1 is a functional module diagram of an enterprise financial data information management system provided by an embodiment of the present invention.

[0078] The enterprise financial data information management system 100 of the present invention can be installed in an electronic device. According to the functions to be implemented, the enterprise financial data information management system 100 can include a classification module 101, a report module 102, a check module 103 and a construction module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0079] In this embodiment, the functions of each module / unit are as follows: The classification module 101 is used to obtain enterprise financial data, perform data analysis on the financial data to obtain structured data, and perform intelligent classification on the structured data to obtain classified data; The reporting module 102 is used to perform trend analysis on the classified data to obtain financial trends, perform abnormality analysis on the classified data using the financial trends to obtain abnormal results, and generate a financial analysis report based on the abnormal results, the classified data, and the financial trends; The checking module 103 is used to perform a compliance check on the analysis report to obtain a compliance result; The construction module 104 is used to construct a distributed ledger according to the compliance result and the analysis report.

[0080] In detail, each module described in the enterprise financial data information management system 100 described in the embodiment of the present invention is used in the same manner as described above. Figures 1 to 3 The technical means are the same as the enterprise financial data information management method described in, and can produce the same technical effects, so I will not go into details here.

[0081] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology.

[0082] Among them, Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0083] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in the system can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for managing enterprise financial data information, characterized in that: The method comprises: Acquire enterprise financial data, perform data analysis on the financial data to obtain structured data, and intelligently classify the structured data to obtain classified data; Performing trend analysis on the classified data to obtain financial trends, performing anomaly analysis on the classified data using the financial trends to obtain anomaly results, and generating a financial analysis report based on the anomaly results, the classified data, and the financial trends; Performing compliance check on the analysis report to obtain compliance results; A distributed ledger is constructed according to the compliance results and the analysis report.

2. A method for managing enterprise financial data information as claimed in claim 1, characterized in that: The data parsing of the financial data to obtain structured data includes: Performing entity recognition on the financial data to obtain named entities; Performing semantic analysis on the financial data according to the named entities to obtain data semantics; extracting key data from the financial data using the field semantics; Performing data standardization on the key data to obtain standardized data; The standardized data is structured and stored to obtain structured data.

3. The enterprise financial data information management method according to claim 1, characterized in that: The intelligently classifying the structured data to obtain the classified data includes: Performing outlier processing on the structured data to obtain preprocessed data; Performing feature extraction on the preprocessed data to obtain feature data; Performing feature standardization on the clustering features of the feature data to obtain clustering features; The pre-processed data is clustered using the clustering features to obtain classified data.

4. A method for managing enterprise financial data information as claimed in claim 3, characterized in that: The performing trend analysis on the classified data to obtain financial trends includes: sorting the classified data in time to obtain a time series; Calculate the trend indicator of the time series; Performing moving average on the time series to obtain smoothed data; Performing trend line fitting on the smoothed data to obtain a trend line graph; A financial trend is generated according to the trend line graph and the trend indicator.

5. The enterprise financial data information management method according to claim 1, characterized in that: The using of the financial trend to perform an abnormal analysis on the classified data to obtain an abnormal result includes: Constructing a trend-guiding feature matrix according to the financial trend and the classification data; Randomly selecting a feature from the trend-guiding feature matrix as a feature to be processed; The trend-guiding feature matrix is ​​divided according to the feature to be processed to obtain a left subset and a right subset; Repeating the segmentation of the left subset and the right subset to obtain an isolated data set; constructing an isolation tree according to the isolation data set; Counting the path length of each data point of the isolated tree species; Calculating an isolation score for each data point in the isolation tree according to the path length; Abnormal results are screened out from the classified data according to the isolation score.

6. A method for managing enterprise financial data information as claimed in claim 5, characterized in that: Generating a financial analysis report according to the abnormal result, the classification data and the financial trend includes: Perform correlation analysis based on the abnormal results and the financial trends to obtain correlation results; Perform abnormal classification analysis according to the abnormal result, the correlation result and the classification data to obtain the abnormal cause; Summarize the data according to the abnormal results and the abnormal reasons to obtain an abnormal summary; Fill in the template according to the financial trend to obtain an overview of the financial trend; The abnormal point summary and the financial trend overview are framed to obtain a financial analysis report.

7. The enterprise financial data information management method according to claim 1, characterized in that: The compliance check of the analysis report to obtain a compliance result includes: Comparing the analysis report with the financial data for data consistency to obtain a comparison result; Performing a sensitive information test on the analysis report to obtain a sensitivity result; The analysis report is scored for compliance according to the sensitivity result and the comparison result to obtain a compliance result.

8. A method for managing enterprise financial data information as claimed in claim 7, characterized in that: The constructing a distributed ledger according to the compliance results and the analysis report includes: Constructing a transaction record from the compliance result and the analysis report; Packing the transaction records into blocks to obtain block package data; Calculating the hash value of the block packet; Linking the block package data to a preset blockchain according to the hash value to obtain a blockchain account book; The blockchain ledger is synchronized in a distributed manner to obtain a distributed ledger.

9. The enterprise financial data information management method according to claim 1, characterized in that: The calculating the hash value of the block packet includes: Serializing the block packet into binary data; Performing byte padding on the binary data to obtain padding data; Blocking the filling data to obtain block data; A cyclic operation is performed on the block data to obtain a hash value.

10. An enterprise financial data information management system, applied to an enterprise financial data information management method according to any one of claims 1 to 9, characterized in that: It includes classification module, reporting module, inspection module and construction module, specifically: A classification module is used to obtain enterprise financial data, perform data analysis on the financial data to obtain structured data, and perform intelligent classification on the structured data to obtain classified data; A reporting module, configured to perform trend analysis on the classified data to obtain financial trends, perform abnormality analysis on the classified data using the financial trends to obtain abnormal results, and generate a financial analysis report based on the abnormal results, the classified data, and the financial trends; A checking module, used for performing a compliance check on the analysis report to obtain a compliance result; A construction module is used to construct a distributed ledger according to the compliance results and the analysis report.

Images