Intelligent generation method and device of financial statements, computer device and storage medium

Abstract

The application relates to the technical field of artificial intelligence, and discloses an intelligent financial statement generation method and device, computer equipment and a storage medium, wherein the method comprises the following steps: obtaining financial statement information to be generated, obtaining a plurality of financial data information, obtaining corresponding data processing logic by using the associated information, processing the financial data information, and obtaining the financial statement.The application has the beneficial effect that the data processing model and the financial information in the database are used to quickly and accurately generate the financial statement, the efficiency of the financial statement merging generation is significantly improved, the manual intervention is reduced, the error rate is reduced, the demand of modern enterprises for rapid decision-making is met, and the financial management level is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent financial statement generation technology, and in particular to an intelligent financial statement generation method, apparatus, computer equipment, and storage medium. Background Technology

[0002] Financial statements are essential written reports on a company's financial position, operating results, and cash flows, typically including a balance sheet, income statement, and cash flow statement. They serve as crucial information for stakeholders (such as investors, creditors, and management) in making decisions. As businesses grow and transactions become more complex, traditional manual generation of financial statements can no longer meet the demands for efficient, accurate, and real-time data. Furthermore, traditional financial reporting processes are time-consuming and error-prone, making them unsuitable for rapid decision-making. Summary of the Invention

[0003] Based on this, it is necessary to address the existing problem of intelligent generation of financial statements by proposing an intelligent generation method, device, computer equipment, and storage medium for financial statements.

[0004] A method for intelligently generating financial statements, the method comprising:

[0005] Retrieve the financial statement information to be generated;

[0006] Based on the financial statement information to be generated, retrieve multiple corresponding financial data from a preset database;

[0007] Obtain the correlation information between the financial data;

[0008] The associated information and the financial statement information to be generated are input into a preset data processing model to obtain the corresponding data processing logic;

[0009] The financial data information is processed according to the data processing logic to obtain financial statement information;

[0010] The financial statement information is imported into a preset template to obtain the corresponding financial statements.

[0011] Furthermore, the step of obtaining the correlation information between the financial data includes:

[0012] Determine whether the preset database contains correlation information between the financial data information;

[0013] If there is no correlation information between the financial data information, the content of the financial data information is converted into a text string, wherein the text string is composed of multiple strings according to their positions in the financial data information;

[0014] Extract key strings from the string corresponding to one of the financial data information, and perform feature matching with the strings corresponding to other financial data information using the BM algorithm;

[0015] Establish the association information between the financial data information based on the matching results.

[0016] Further, the step of inputting the associated information and the financial statement information to be generated into a preset data processing model to obtain the corresponding data processing logic includes:

[0017] Temporary processing logic is calculated based on the aforementioned associated information;

[0018] Through formula Calculate the first matching degree between each of the temporary processing logics and the financial statement information to be generated; wherein... This represents the vector corresponding to the temporary processing logic. This represents the vector corresponding to the financial statement information to be generated. Indicates the first degree of match;

[0019] Determine whether the first matching degree corresponding to each of the temporary processing logics reaches the first preset matching degree value;

[0020] The temporary processing logic that reaches the first preset matching degree value is used as the data processing logic.

[0021] Further, the step of calculating the temporary processing logic based on the associated information includes:

[0022] Each of the aforementioned financial data information is vectorized to obtain its corresponding n-dimensional vector;

[0023] The n-dimensional vectors corresponding to the aforementioned financial data are weighted and calculated to obtain an n-dimensional target vector, denoted as x1, x2, ..., xn. n ;

[0024] Multiple temporary processing logics are obtained by calculating G(t) = softmax[Vf(t)]; where f(t) = g[Ux t +Wf(t-1)+b], where G(t) is the temporary processing logic obtained by inputting the t-th target vector, x t Let V represent the t-th target vector, f(t) represent the intermediate function obtained by inputting the t-th target vector, and f(t-1) represent the intermediate function obtained by inputting the (t-1)-th target vector. V, U, W, and b are all preset parameters.

[0025] Furthermore, prior to the step of obtaining the correlation information between the financial data, the method further includes:

[0026] According to the formula Calculate the outliers for each data point in each financial data item; where Z ij Let μ represent the outlier of the i-th data point in the j-th financial data point, and let μ represent the average value of all data points in the j-th financial data point. σ represents the standard deviation of the j financial data points, and x ij This represents the i-th data in the j-th financial data information, and n represents the number of data in the j-th financial data information;

[0027] |Z ij |>Z thr The corresponding target data is extracted and compared with the actual information of the financial data; where Z thr The set parameter value;

[0028] If the comparison result indicates that the target data is incorrect, then the correct actual data will replace the target data.

[0029] Furthermore, before the step of importing the financial statement information into a preset template to obtain the corresponding financial statements, the method further includes:

[0030] Send multiple financial report templates to the corresponding users;

[0031] Obtain the financial report template selected by the user as the preset template.

[0032] Further, the step of processing the financial data information according to the data processing logic to obtain financial statement information includes:

[0033] The financial data is cleaned, categorized, and summarized to obtain the target financial data.

[0034] Extract the preset key indicator data from the target financial data;

[0035] The financial statement information is obtained by analyzing and predicting based on the key indicator data.

[0036] A smart financial statement generation device, the device comprising:

[0037] The first acquisition module is used to acquire the financial statement information to be generated;

[0038] The second acquisition module is used to acquire multiple corresponding financial data information from a preset database based on the financial statement information to be generated;

[0039] The third acquisition module is used to acquire the correlation information between the financial data information;

[0040] The input module is used to input the associated information and the financial statement information to be generated into a preset data processing model to obtain the corresponding data processing logic;

[0041] The processing module is used to process the financial data information according to the data processing logic to obtain financial statement information;

[0042] The import module is used to import the financial statement information into a preset template to obtain the corresponding financial statements.

[0043] A computer device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the following steps:

[0044] Retrieve the financial statement information to be generated;

[0045] Based on the financial statement information to be generated, retrieve multiple corresponding financial data from a preset database;

[0046] Obtain the correlation information between the financial data;

[0047] The associated information and the financial statement information to be generated are input into a preset data processing model to obtain the corresponding data processing logic;

[0048] The financial data information is processed according to the data processing logic to obtain financial statement information;

[0049] The financial statement information is imported into a preset template to obtain the corresponding financial statements.

[0050] A computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the following steps:

[0051] Retrieve the financial statement information to be generated;

[0052] Based on the financial statement information to be generated, retrieve multiple corresponding financial data from a preset database;

[0053] Obtain the correlation information between the financial data;

[0054] The associated information and the financial statement information to be generated are input into a preset data processing model to obtain the corresponding data processing logic;

[0055] The financial data information is processed according to the data processing logic to obtain financial statement information;

[0056] The financial statement information is imported into a preset template to obtain the corresponding financial statements.

[0057] The beneficial effects of this invention are as follows: By acquiring the financial statement information to be generated and obtaining multiple financial data information, using their correlation information to obtain the corresponding data processing logic, and processing the financial data information to obtain financial statements, the invention achieves the rapid and accurate generation of financial statements by utilizing the data processing model and financial information in the database. This significantly improves the efficiency of consolidated financial statement generation, reduces manual intervention, lowers the error rate, adapts to the needs of modern enterprises for rapid decision-making, and helps to improve the level of financial management. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] in:

[0060] Figure 1 This is an application environment diagram of the intelligent financial statement generation method in one embodiment;

[0061] Figure 2 This is a flowchart of a method for intelligently generating financial statements in one embodiment;

[0062] Figure 3 This is a structural block diagram of an intelligent financial statement generation device in one embodiment;

[0063] Figure 4 This is a structural block diagram of a computer device in one embodiment. Detailed Implementation

[0064] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0065] Figure 1 This is a diagram illustrating the application environment for intelligent financial statement generation in one embodiment. (Refer to...) Figure 1This intelligent financial statement generation method is applied to an intelligent financial statement generation system. The system includes a terminal 110 and a server 120. The terminal 110 and server 120 are connected via a network. The terminal 110 can be a desktop terminal or a mobile terminal; a mobile terminal can be at least one of a mobile phone, tablet, or laptop. The server 120 can be a standalone server or a server cluster consisting of multiple servers. The terminal 110 is used to acquire financial data, and the server 120 is used to store the financial data.

[0066] like Figure 2 As shown, in one embodiment, a method for intelligently generating financial statements is provided. This method can be applied to both terminals and servers; this embodiment uses terminal application as an example. The intelligent generation method for financial statements specifically includes the following steps:

[0067] S1: Obtain the financial statement information to be generated;

[0068] S2: Obtain multiple corresponding financial data from a preset database based on the financial statement information to be generated;

[0069] S3: Obtain the correlation information between the financial data information;

[0070] S4: Input the associated information and the financial statement information to be generated into the preset data processing model to obtain the corresponding data processing logic;

[0071] S5: Process the financial data information according to the data processing logic to obtain financial statement information;

[0072] S6: Import the financial statement information into a preset template to obtain the corresponding financial statements.

[0073] As described in step S1 above, obtain the financial statement information to be generated. It is necessary to identify the type of financial statement the user needs to generate (e.g., balance sheet, income statement, cash flow statement, etc.), as well as the specific time period and any other relevant parameters (e.g., company or department). This information can be obtained through manual upload or by customizing some financial statement information and then having the user select it themselves.

[0074] As described in step S2 above, multiple corresponding financial data information are obtained from a preset database based on the financial statement information to be generated. The preset database (e.g., an ERP system, financial software, or a data warehouse) is accessed, and relevant financial data is extracted from it. The relevant financial data may include sales data, cost data, expense data, asset and liability data, etc., and can be obtained from the preset database through web scraping or other methods.

[0075] As described in step S3 above, the correlation information between the financial data is obtained. The extracted financial data is analyzed to identify the correlation between them. Here, the correlation information is the related part between two pieces of financial data. For example, one piece of financial data is a list of various expenditures, while the other piece of financial data is the specific information of an expenditure. Therefore, the corresponding correlation information is to find the specific information of that expenditure, that is, the content of the other piece of financial data can be linked through one piece of financial data.

[0076] As described in step S4 above, the associated information and the financial statement information to be generated are input into a preset data processing model to obtain the corresponding data processing logic. The preset data processing model (which can be a machine learning model or a rule-based model) analyzes the associated information and the statement information to be generated. This model will generate the required data processing logic, specifically a string of processing code. This code can be used for data scraping, or for adding, modifying, or deleting data. Therefore, by inputting this code into the preset data processing model, the data processing logic can be obtained based on the corresponding association.

[0077] As described in step S5 above, the financial data information is processed according to the data processing logic to obtain financial statement information. The financial data is calculated and processed through the data processing logic. This processing may include summarization, classification, averaging, ratio calculation, etc., ultimately generating financial statement information that complies with accounting standards.

[0078] As described in step S6 above, the financial statement information is imported into a preset template to obtain the corresponding financial statements. The processed financial statement information is then imported into a specific report template in a preset format (such as Excel, PDF, or other report formats). This ensures the generated financial statements have a clear structure, facilitating reading and analysis. Utilizing data processing models and financial information in the database enables the rapid and accurate generation of financial statements, significantly improving the efficiency of consolidated financial statement generation, reducing manual intervention, lowering error rates, adapting to the needs of modern enterprises for rapid decision-making, and contributing to improved financial management.

[0079] In one embodiment, step S3, which involves obtaining the correlation information between the financial data, includes:

[0080] S301: Determine whether the preset database contains correlation information between the financial data information;

[0081] S302: If there is no correlation information between the financial data information, the content in the financial data information is converted into a text string, wherein the text string is composed of multiple strings according to their positions in the financial data information;

[0082] S303: Extract the key string from the string corresponding to one of the financial data information, and perform feature matching with the strings corresponding to other financial data information using the BM algorithm;

[0083] S304: Establish the association information between the financial data information based on the matching results.

[0084] As described in steps S301-S304 above, since some financial data information was not associated with other financial data information before being entered into the preset database, it lacks association information, making it impossible to obtain specific data content based on association information later. Therefore, it is possible to detect whether the selected target financial data information has association information in the preset database. When there is no association information between financial data information, an association relationship can be established between the preset databases as the association information between the target medical databases. The specific establishment method is as follows: first, the content in the financial data information is converted into individual strings; then, key strings are extracted based on a machine learning model in natural language processing; and then, the feature matching between the preset databases is calculated using the BM (Boyer-Moore) algorithm. The BM algorithm is an efficient algorithm for string search, particularly suitable for finding pattern strings in text. The association information between the target financial data information is then established. It should be noted that the various financial data information generally have complex association information; the above method can only establish relatively simple association information.

[0085] In one embodiment, step S4, which involves inputting the associated information and the financial statement information to be generated into a preset data processing model to obtain the corresponding data processing logic, includes:

[0086] S401: Calculate temporary processing logic based on the associated information;

[0087] S402: Through formula Calculate the first matching degree between each of the temporary processing logics and the financial statement information to be generated; wherein... This represents the vector corresponding to the temporary processing logic. This represents the vector corresponding to the financial statement information to be generated. Indicates the first degree of match;

[0088] S403: Determine whether the first matching degree corresponding to each of the temporary processing logics has reached the first preset matching degree value;

[0089] S404: The temporary processing logic that reaches the first preset matching degree value is used as the data processing logic.

[0090] As described in steps S401-S404 above, the acquisition of data processing logic is achieved. Based on the correlation information, all corresponding temporary processing logics can be calculated. The calculation method can be based on training with big data. The training sample data consists of multiple correlation relationships and the computational logic built upon these relationships. This sample data can be obtained through big data. To simplify the number of temporary processing logics generated, temporary processing logics unrelated to the financial statement can be removed. Specifically, a formula can be used to calculate the first matching degree between each temporary processing logic and the financial statement information to be generated. When the first matching degree reaches a first preset matching degree value, the corresponding temporary processing logic can be used as the data processing logic. Here, the first preset matching degree is a pre-set value. The matching degree algorithm can be any algorithm, such as the WMD algorithm (Word Mover's Dilemma), a cosine similarity-based algorithm, a similarity algorithm, a similarity algorithm, or an SVM (Support Vector Machine) vector model, etc. Preferably, it uses a similarity algorithm. The calculation is performed, and when the calculation result is close to 1, it means that the temporary processing logic is more relevant to the financial statement information to be generated. When the calculation result is close to 0, it means that the temporary processing logic is less relevant to the financial statement information to be generated. The temporary processing logic whose calculation result reaches the first preset matching degree is used as the data processing logic and participates in the subsequent calculation and analysis. Therefore, the temporary processing logic that is not the data processing logic can be omitted and does not need to participate in the subsequent calculation process, thus saving calculation time.

[0091] In one embodiment, step S401, which calculates the temporary processing logic based on the associated information, includes:

[0092] S4011: Vectorize each of the aforementioned financial data information to obtain their respective n-dimensional vectors;

[0093] S4012: Weight the n-dimensional vectors corresponding to the respective financial data information to obtain an n-dimensional target vector, denoted as x1, x2, ..., xn.n ;

[0094] S4013: Multiple temporary processing logics are obtained by calculating G(t) = softmax[Vf(t)]; where f(t) = g[Ux t +Wf(t-1)+b], where G(t) is the temporary processing logic obtained by inputting the t-th target vector, x t Let V represent the t-th target vector, f(t) represent the intermediate function obtained by inputting the t-th target vector, and f(t-1) represent the intermediate function obtained by inputting the (t-1)-th target vector. V, U, W, and b are all preset parameters.

[0095] As described in steps S4011-S4013 above, the specific formula for obtaining the temporary processing logic can be as follows: First, the financial data information is vectorized separately, and then a weighted calculation is performed. The weighted calculation method can be by calculating the mathematical average or geometric average and then adding them together, that is, integrating the related information so that the generated n-dimensional target vector integrates the content of the financial data information. The weighted calculation method is not limited and can be used to integrate the information of the two. Then, multiple temporary processing logics are calculated by the formula G(t) = softmax[Vf(t)]. G(t) is the temporary processing logic obtained by inputting the t-th target vector, and softmax is the softmax function. The temporary processing logic is related to the dimension of the vector. That is, the more complex the financial data information, the more temporary processing logics are generated. In addition, V, U, W, and b are all parameter values ​​obtained through training. When the t-th target vector is input, the t-th operation logic can be obtained.

[0096] In one embodiment, before step S3 of obtaining the correlation information between the financial data information, the method further includes:

[0097] S201: According to the formula Calculate the outliers for each data point in each financial data item; where Z ij Let μ represent the outlier of the i-th data point in the j-th financial data point, and let μ represent the average value of all data points in the j-th financial data point. σ represents the standard deviation of the j financial data points, and x ij This represents the i-th data in the j-th financial data information, and n represents the number of data in the j-th financial data information;

[0098] S202: |Z ij |>Z thr The corresponding target data is extracted and compared with the actual information of the financial data; where Z thrThe set parameter value;

[0099] S203: If the comparison result indicates that the target data is incorrect, then replace the target data with the correct actual data.

[0100] As described in steps S201-S203 above, since some data may contain errors during the statistical process, it is necessary to calculate the data in the financial data after obtaining the financial data information. The outlier of each data in the financial data information is calculated. When the outlier exceeds the set parameter value, the data can be considered abnormal. Of course, it is not ruled out that the data is a normal data value. For example, the business department may have made a large profit in a certain month, while the profit in other months is far below the normal value. Therefore, this application only extracts the outlier. Whether it is a normal value still needs to be judged later. That is, the actual information is compared with the target data. When the comparison is incorrect, the correct actual data is replaced with the target data to ensure the reliability of the generated financial statements.

[0101] In one embodiment, before step S6 of importing the financial statement information into a preset template to obtain the corresponding financial statement, the method further includes:

[0102] S501: Send multiple financial report templates to the corresponding users;

[0103] S502: Obtain the financial report template selected by the user as the preset template.

[0104] As described in steps S501-S502 above, multiple preset financial report template options are provided to users (e.g., finance personnel or management). These templates can be based on standard financial report formats or customized according to user needs. Templates can be sent via various methods such as email, internal system notifications, or real-time application programming interfaces (APIs) to ensure easy user access. Samples or brief descriptions of the templates are shown to help users understand the main features and applicable scenarios of each template. Users select the financial report template that best suits their needs from the provided templates. In some embodiments, the system records the user's selection to ensure that subsequent financial statement generation uses the selected template. This selection process can be performed through a graphical user interface (GUI) or other interactive methods.

[0105] In one embodiment, step S5, which processes the financial data information according to the data processing logic to obtain financial statement information, includes:

[0106] S511: Perform data cleaning, classification and summarization on the financial data to obtain the target financial data;

[0107] S512: Extract the preset key indicator data from the target financial data;

[0108] S513: Based on the key indicator data, analyze and predict to obtain the financial statement information.

[0109] As described in steps S511-S513 above, data cleaning includes examining the extracted financial data, identifying and correcting erroneous or incomplete data records. This includes, for example, removing duplicates, filling in missing values, and correcting formatting errors. Data classification involves organizing the financial data according to predefined categories (such as assets, liabilities, revenue, expenses, etc.) for further processing. This ensures the data is structured and manageable. Data summarization involves summarizing the classified data, such as calculating totals, averages, or other statistical indicators. This process helps transform large amounts of data into a target data format that is easy to analyze.

[0110] Reference Figure 3 The present invention also provides an intelligent financial statement generation device, the device comprising:

[0111] The first acquisition module 10 is used to acquire the financial statement information to be generated;

[0112] The second acquisition module 20 is used to acquire multiple corresponding financial data information from a preset database based on the financial statement information to be generated;

[0113] The third acquisition module 30 is used to acquire the correlation information between the financial data information;

[0114] Input module 40 is used to input the associated information and the financial statement information to be generated into a preset data processing model to obtain the corresponding data processing logic;

[0115] Processing module 50 is used to process the financial data information according to the data processing logic to obtain financial statement information;

[0116] Import module 60 is used to import the financial statement information into a preset template to obtain the corresponding financial statements.

[0117] In one embodiment, the third acquisition module 30 includes:

[0118] The association information determination submodule is used to determine whether the preset database contains association information between the financial data information;

[0119] The text string conversion submodule is used to convert the content of the financial data information into a text string if there is no correlation information between the financial data information, wherein the text string is composed of multiple strings according to their positions in the financial data information;

[0120] The string extraction submodule is used to extract key strings from the strings corresponding to one of the financial data information, and to perform feature matching with the strings corresponding to other financial data information using the BM algorithm.

[0121] The association information establishment submodule is used to establish association information between the financial data information based on the matching results.

[0122] In one embodiment, the input module 40 includes:

[0123] The first calculation submodule is used to calculate temporary processing logic based on the associated information;

[0124] The second calculation submodule is used to calculate using formulas. Calculate the first matching degree between each of the temporary processing logics and the financial statement information to be generated; wherein... This represents the vector corresponding to the temporary processing logic. This represents the vector corresponding to the financial statement information to be generated. Indicates the first degree of match;

[0125] The matching degree determination submodule is used to determine whether the first matching degree corresponding to each of the temporary processing logics has reached the first preset matching degree value;

[0126] As a submodule, it is used to use the temporary processing logic that reaches the first preset matching degree value as the data processing logic.

[0127] In one embodiment, the first computing submodule includes:

[0128] The vectorization unit is used to vectorize each of the financial data information to obtain their respective n-dimensional vectors.

[0129] The weighted calculation unit is used to perform weighted calculations on the n-dimensional vectors corresponding to the financial data information to obtain n-dimensional target vectors, namely x1, x2, ..., xn. n ;

[0130] The temporary processing logic calculation unit is used to calculate multiple temporary processing logics through G(t) = softmax[Vf(t)]; where f(t) = g[Ux t +Wf(t-1)+b], where G(t) is the temporary processing logic obtained by inputting the t-th target vector, x tLet V represent the t-th target vector, f(t) represent the intermediate function obtained by inputting the t-th target vector, and f(t-1) represent the intermediate function obtained by inputting the (t-1)-th target vector. V, U, W, and b are all preset parameters.

[0131] In one embodiment, the apparatus further includes:

[0132] The outlier calculation module is used to calculate outliers based on the formula. Calculate the outliers for each data point in each financial data item; where Z ij Let μ represent the outlier of the i-th data point in the j-th financial data point, and let μ represent the average value of all data points in the j-th financial data point. σ represents the standard deviation of the j financial data points, and x ij This represents the i-th data in the j-th financial data information, and n represents the number of data in the j-th financial data information;

[0133] The target data extraction module is used to extract |Z ij |>Z thr The corresponding target data is extracted and compared with the actual information of the financial data; where Z thr The set parameter value;

[0134] The replacement module is used to replace the target data with the correct actual data if the comparison result indicates that the target data is incorrect.

[0135] In one embodiment, the apparatus further includes:

[0136] The financial report template sending module is used to send multiple financial report templates to the corresponding users;

[0137] The financial report template acquisition module is used to acquire the financial report template selected by the user as the preset template.

[0138] In one embodiment, the processing module 50 includes:

[0139] The cleaning submodule is used to clean, classify, and summarize the financial data to obtain the target financial data.

[0140] The key indicator data extraction submodule is used to extract preset key indicator data from the target financial data;

[0141] The analysis submodule is used to analyze and predict based on the key indicator data to obtain the financial statement information.

[0142] The beneficial effects of this invention are as follows: By acquiring the financial statement information to be generated and obtaining multiple financial data information, using their correlation information to obtain the corresponding data processing logic, and processing the financial data information to obtain financial statements, the invention achieves the rapid and accurate generation of financial statements by utilizing the data processing model and financial information in the database. This significantly improves the efficiency of consolidated financial statement generation, reduces manual intervention, lowers the error rate, adapts to the needs of modern enterprises for rapid decision-making, and helps to improve the level of financial management.

[0143] Figure 4 An internal structural diagram of a computer device in one embodiment is shown. This computer device can specifically be a terminal or a server. Figure 4 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program enables the processor to implement a method for intelligently generating financial statements. The internal memory may also store a computer program, which, when executed by the processor, enables the processor to execute the method for intelligently generating financial statements. Those skilled in the art will understand that... Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0144] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the following steps:

[0145] Retrieve the financial statement information to be generated;

[0146] Based on the financial statement information to be generated, retrieve multiple corresponding financial data from a preset database;

[0147] Obtain the correlation information between the financial data;

[0148] The associated information and the financial statement information to be generated are input into a preset data processing model to obtain the corresponding data processing logic;

[0149] The financial data information is processed according to the data processing logic to obtain financial statement information;

[0150] The financial statement information is imported into a preset template to obtain the corresponding financial statements.

[0151] By leveraging data processing models and financial information in databases, financial statements can be generated quickly and accurately, significantly improving the efficiency of consolidated financial statement generation, reducing manual intervention, lowering error rates, adapting to the needs of modern enterprises for rapid decision-making, and helping to improve financial management.

[0152] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the following steps:

[0153] Retrieve the financial statement information to be generated;

[0154] Based on the financial statement information to be generated, retrieve multiple corresponding financial data from a preset database;

[0155] Obtain the correlation information between the financial data;

[0156] The associated information and the financial statement information to be generated are input into a preset data processing model to obtain the corresponding data processing logic;

[0157] The financial data information is processed according to the data processing logic to obtain financial statement information;

[0158] The financial statement information is imported into a preset template to obtain the corresponding financial statements.

[0159] By leveraging data processing models and financial information in databases, financial statements can be generated quickly and accurately, significantly improving the efficiency of consolidated financial statement generation, reducing manual intervention, lowering error rates, adapting to the needs of modern enterprises for rapid decision-making, and helping to improve financial management.

[0160] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAM bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0161] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0162] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for intelligent generation of financial statements, characterized in that, The method comprises: acquiring financial statement information to be generated; acquiring corresponding financial data information from a preset database according to the financial statement information to be generated; acquiring association information between the financial data information; inputting the association information and the financial statement information to be generated into a preset data processing model to acquire corresponding data processing logic; processing the financial data information according to the data processing logic to obtain financial statement information; importing the financial statement information into a preset template to obtain corresponding financial statements; the step of inputting the association information and the financial statement information to be generated into a preset data processing model to acquire corresponding data processing logic comprises: calculating temporary processing logic based on the association information; The first matching degree of each said temporary processing logic and said financial statement information to be generated is calculated by formula represents a vector corresponding to temporary processing logic, represents a vector corresponding to financial statement information to be generated, represents the first matching degree;​ judging whether the first matching degree corresponding to each temporary processing logic reaches a first preset matching degree value; regarding the temporary processing logic reaching the first preset matching degree value as the data processing logic; the step of calculating temporary processing logic based on the association information comprises: vectorizing each of the financial data information to obtain a corresponding n-dimensional vector; performing weighted calculation on the n-dimensional vector corresponding to each of the financial data information to obtain an n-dimensional target vector, respectively x1, x2, …, xn; By A plurality of temporary processing logics are calculated; wherein G(t) is the temporary processing logic obtained by inputting the tth target vector, xt represents the tth target vector, represents the intermediate function obtained by inputting the tth target vector, represents the intermediate function obtained by inputting the (t-1)th target vector, V, U, W, and b are all preset parameters.

2. The method of intelligent generation of financial statements as claimed in claim 1, wherein, the step of acquiring association information between the financial data information comprises: judging whether the preset database has association information between the financial data information; if the preset database does not have association information between the financial data information, converting the content in the financial data information into a text string, wherein the text string is composed of a plurality of character strings according to their positions in the financial data information; extracting a key character string from the character string corresponding to one of the financial data information, and performing feature matching on the character strings corresponding to other financial data information through a BM algorithm; establishing association information between the financial data information according to the matching result. 3.The method of claim 1, wherein, Before the step of acquiring association information between the financial data information, the method further comprises: According to the formula Calculate the outliers in each data point within each financial data entry; where... Indicates the first An outlier in the i-th data in the aforementioned financial data information. Indicates the first The average value of each data point in the aforementioned financial data information, and , express The standard deviation of the aforementioned financial data information, and , Indicates the first The i-th data in the aforementioned financial data information, where n represents the i-th data. The number of data in the aforementioned financial data information; Will The corresponding target data is extracted and compared with the actual information in the financial data; wherein The set parameter value; if the comparison result is that the target data is incorrect, replacing the target data with correct actual data.

4. The method of intelligent generation of financial statements as claimed in claim 1, wherein, Before the step of importing the financial statement information into a preset template to obtain corresponding financial statements, the method further comprises: sending a plurality of financial report templates to a corresponding user; acquiring a financial report template selected by the user as the preset template.

5. The method of intelligent generation of financial statements as claimed in claim 1, wherein, The step of processing the financial data information according to the data processing logic to obtain financial statement information comprises: performing data cleaning, classification and summarization on the financial data to obtain target financial data; extracting preset key indicator data in the target financial data; performing analysis and prediction based on the key indicator data to obtain the financial statement information.

6. An apparatus for intelligent generation of financial statements, characterized by The device comprises: a first acquisition module for acquiring financial statement information to be generated; a second acquisition module for acquiring corresponding financial data information from a preset database according to the financial statement information to be generated; A third obtaining module is configured to obtain association information between the financial data information; An input module is configured to input the association information and the to-be-generated financial report information into a preset data processing model to obtain corresponding data processing logic; A processing module is configured to process the financial data information according to the data processing logic to obtain financial report information; An importing module is configured to import the financial report information into a preset template to obtain a corresponding financial report; The input module comprises: A first calculation submodule is configured to calculate temporary processing logic based on the association information; a second calculation sub-module, configured to calculate a first matching degree between each of the temporary processing logics and the financial statement information to be generated by a formula represents a vector corresponding to the temporary processing logic, represents a vector corresponding to the financial statement information to be generated, represents the first matching degree;​ A matching degree judgment submodule is configured to judge whether the first matching degree corresponding to each temporary processing logic reaches a first preset matching degree value; A submodule is configured to take the temporary processing logic that reaches the first preset matching degree value as the data processing logic; The first calculation submodule comprises: A vectorization unit is configured to vectorize each piece of financial data information to obtain a corresponding n-dimensional vector; A weighted calculation unit is configured to perform weighted calculation on the n-dimensional vector corresponding to each piece of financial data information to obtain an n-dimensional target vector, respectively x1, x2, …, xn; a temporary processing logic calculation unit, configured to calculate a plurality of temporary processing logics by wherein G(t) is the temporary processing logic obtained by inputting the tth target vector, xt represents the tth target vector, represents an intermediate function obtained by inputting the tth target vector, represents an intermediate function obtained by inputting the (t-1)th target vector, and V, U, W and b are all preset parameters.

7. A computer-readable storage medium, characterized in that, The device comprises a memory and a processor, and the memory stores a computer program which, when executed by the processor, causes the processor to perform the steps of the intelligent financial report generation method according to any one of claims 1 to 5.

8. A computer device, comprising: The device comprises a memory and a processor, and the memory stores a computer program which, when executed by the processor, causes the processor to perform the steps of the intelligent financial report generation method according to any one of claims 1 to 5.

Images