A financial audit method and device, electronic equipment and storage medium

Abstract

The application discloses a financial audit method and device, electronic equipment and storage medium. The method comprises the following steps: in response to a financial audit question input by a user, determining a task type corresponding to the financial audit question; in the case that the task type corresponding to the financial audit question is a structured query language query task, determining a structured query language query statement corresponding to the financial audit question, executing the structured query language query statement, and obtaining a structured query language query result; in the case that the task type corresponding to the financial audit question is a text understanding task, searching the financial audit question in a financial audit document to obtain associated text corresponding to the financial audit question, and generating a document query result based on the associated text corresponding to the financial audit question. The above technical solution classifies the input financial audit question to perform structured query language query or document query, thereby quickly obtaining the query result of the financial audit question, and effectively improving the financial audit efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a financial audit method and device, electronic equipment and a storage medium. BACKGROUND

[0002] In traditional financial audit, the audit work mainly relies on manual processing. With the increase of business volume, the traditional financial audit method cannot meet the demand.

[0003] In the implementation of the present application, it is found that the prior art has at least the following technical problems: the existing financial audit method has the problem of low audit efficiency. SUMMARY

[0004] The present application provides a financial audit method and device, electronic equipment and a storage medium to improve the efficiency of financial audit.

[0005] According to an aspect of the present application, a financial audit method is provided, comprising:

[0006] In response to a user input financial audit question, determining the task type corresponding to the financial audit question;

[0007] In the case where the task type corresponding to the financial audit question is a structured query language query task, determining the structured query language query statement corresponding to the financial audit question, executing the structured query language query statement corresponding to the financial audit question, and obtaining the structured query language query result corresponding to the financial audit question;

[0008] In the case where the task type corresponding to the financial audit question is a text understanding task, searching the financial audit document for the financial audit question to obtain the associated text corresponding to the financial audit question, and generating the document query result corresponding to the financial audit question based on the associated text corresponding to the financial audit question.

[0009] According to another aspect of the present application, a financial audit device is provided, comprising:

[0010] A financial audit question type determination module for determining the task type corresponding to the financial audit question in response to a user input financial audit question;

[0011] A structured query language query result determination module for determining the structured query language query statement corresponding to the financial audit question in the case where the task type corresponding to the financial audit question is a structured query language query task, executing the structured query language query statement corresponding to the financial audit question, and obtaining the structured query language query result corresponding to the financial audit question;

[0012] The document query result determination module is configured to, in a case where the task type corresponding to the financial audit question is a text understanding task, search the financial audit question in a financial audit document to obtain associated text corresponding to the financial audit question, and generate a document query result corresponding to the financial audit question based on the associated text corresponding to the financial audit question.

[0013] According to another aspect of the present application, there is provided an electronic device comprising:

[0014] at least one processor;

[0015] and a memory connected to the at least one processor in communication;

[0016] wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the financial audit method according to any one of the embodiments of the present application.

[0017] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to perform the financial audit method according to any one of the embodiments of the present application when executed by the processor.

[0018] The technical solution of the embodiments of the present application determines the task type corresponding to the financial audit question in response to the user input financial audit question, determines the structured query language (SQL) query statement corresponding to the financial audit question in a case where the task type corresponding to the financial audit question is a SQL query task, executes the SQL query statement corresponding to the financial audit question to obtain the SQL query result corresponding to the financial audit question, and searches the financial audit question in a financial audit document to obtain the associated text corresponding to the financial audit question in a case where the task type corresponding to the financial audit question is a text understanding task, and generates the document query result corresponding to the financial audit question based on the associated text corresponding to the financial audit question. The above technical solution classifies the user input financial audit question to perform SQL query or document query, thereby quickly obtaining the query result of the financial audit question, and effectively improving the financial audit efficiency.

[0019] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to make the technical solution in the embodiments of the present application clearer, the drawings needed in the embodiments description will be briefly introduced as follows. Obviously, the drawings in the embodiments description are only some of the embodiments of the present application, and all the other embodiments obtained by those skilled in the art without any creative effort based on the embodiments in the present application should belong to the protection scope of the present application.

[0021] Figure 1 is a flow chart of a financial audit method according to the first embodiment of the present application;

[0022] Figure 2 is a flow chart of a financial audit method according to the second embodiment of the present application;

[0023] Figure 3 is a flow chart of a financial audit method according to the third embodiment of the present application;

[0024] Figure 4 is a flow chart of a financial audit method according to the fourth embodiment of the present application;

[0025] Figure 5 is a structural schematic diagram of a financial audit device according to the fifth embodiment of the present application;

[0026] Figure 6 is a structural schematic diagram of an electronic device implementing the financial audit method of the present application. DETAILED DESCRIPTION

[0027] In order to make the technical solution in the embodiments of the present application clearer, the drawings needed in the embodiments description will be briefly introduced as follows. Obviously, the drawings in the embodiments description are only some of the embodiments of the present application, and all the other embodiments obtained by those skilled in the art without any creative effort based on the embodiments in the present application should belong to the protection scope of the present application.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of the present application complies with the relevant provisions of national laws and regulations.

[0029] Embodiment one

[0030] Figure 1 A flowchart of a financial audit method provided for the first embodiment of the present application. This embodiment can be applied to the case of financial audit by a large language model. The method can be executed by a financial audit device, which can be realized in the form of hardware and / or software, and can be configured in an electronic device such as a terminal and / or a server. As shown in the figure, the method comprises: Figure 1

[0031] S110, in response to the financial audit question input by the user, determining the task type corresponding to the financial audit question.

[0032] In the embodiments of the present application, the financial audit question refers to a question related to financial audit.

[0033] For example, the user can input a question related to financial audit through a question and answer interaction interface, for example, the financial audit question can be "query the top 3 projects in 2021" or "how to determine the allocation ratio of project funds in the photovoltaic power generation prediction project?" and the like.

[0034] In the embodiments of the present application, the task type is a structured query language (SQL) query task or a text understanding task. The SQL query task refers to a question type that converts the financial audit question into an SQL query statement and then queries in the SQL database through the SQL query statement. The text understanding task refers to a question type that searches in the financial audit document. It should be noted that the answer to the financial audit question may exist in the SQL database or in the financial audit document. By determining the task type corresponding to the financial audit question, it can be determined whether to search for the question answer in the SQL database or in the financial audit document, thereby improving the financial audit query efficiency. ​

[0035] S120, in the case that the task type corresponding to the financial audit question is a structured query language query task, determining a structured query language query statement corresponding to the financial audit question, executing the structured query language query statement corresponding to the financial audit question, and obtaining a structured query language query result corresponding to the financial audit question.

[0036] The structured query language query result refers to a query result of the SQL query statement in the SQL database.

[0037] Specifically, in the case that the task type corresponding to the financial audit question is an SQL query task, the SQL statement conversion is performed on the financial audit question, an SQL query statement corresponding to the financial audit question is obtained, the SQL query statement corresponding to the financial audit question is executed, the query structure of the SQL query statement in the SQL database is obtained, and an SQL query result corresponding to the financial audit question is obtained.

[0038] S130, in the case that the task type corresponding to the financial audit question is a text understanding task, searching the financial audit question in a financial audit document to obtain associated text corresponding to the financial audit question, and generating a document query result corresponding to the financial audit question based on the associated text corresponding to the financial audit question.

[0039] The financial audit document refers to a file that needs to be searched and analyzed in the financial audit process. For example, the financial audit document can be a photovoltaic power generation prediction project file or a project contract. The associated text refers to words, sentences or paragraphs associated with the financial audit question searched from the financial audit document, which is not limited herein. The document query result refers to an answer obtained by searching and analyzing the financial audit question in the financial audit document.

[0040] For example, the financial audit question can be “What is the fixed asset depreciation method of our company?”, and the associated text searched in the financial audit document can be “In 2019, our company adopts the straight-line method to depreciate fixed assets, and the estimated residual value is 5%, and the depreciation period is 5 years”. The document query result can be “Our company adopts the straight-line method to depreciate fixed assets”.

[0041] In some optional embodiments, the financial audit document can be a pdf file or a word file, and the pdf file or the word file can be subjected to text extraction and data cleaning to obtain a Markdown format table, so that the financial audit question can be searched in the Markdown format table to improve the searching speed and the searching quality.

[0042] Optionally, the document query result corresponding to the financial audit question is generated based on the associated text corresponding to the financial audit question, including: constructing an audit document retrieval prompt based on the financial audit question and the associated text corresponding to the financial audit question; inputting the audit document retrieval prompt into a large language model to obtain the document query result corresponding to the financial audit question.

[0043] The audit document retrieval prompt is a reference data for guiding the large language model to output answers.

[0044] It should be noted that the audit document retrieval prompt can guide the large language model to make full use of the associated text to answer efficiently and accurately, thereby improving the accuracy of the document query result.

[0045] The technical scheme of the embodiment of the application, in response to the user input financial audit question, determines the task type corresponding to the financial audit question, in the case that the task type corresponding to the financial audit question is a structured query language query task, determines the structured query language query statement corresponding to the financial audit question, executes the structured query language query statement corresponding to the financial audit question, and obtains the structured query language query result corresponding to the financial audit question; in the case that the task type corresponding to the financial audit question is a text understanding task, the financial audit question is retrieved in the financial audit document to obtain the associated text corresponding to the financial audit question, and the document query result corresponding to the financial audit question is generated based on the associated text corresponding to the financial audit question. The above technical scheme classifies the user input financial audit question to perform SQL query or document query, thereby realizing quick acquisition of the query result of the financial audit question and effectively improving the financial audit efficiency.

[0046] Embodiment two

[0047] Figure 2 A flowchart of a financial audit method provided by the second embodiment of the application is provided, and the method of the embodiment can be combined with each optional scheme of the financial audit method provided in the above embodiments. The financial audit method provided by the embodiment is further optimized. Optionally, the determination of the task type corresponding to the financial audit question includes: constructing a query target determination prompt based on the historical question and answer information and the financial audit question; inputting the query target determination prompt into a large language model to obtain the query target corresponding to the financial audit question; and classifying the query target corresponding to the financial audit question to obtain the task type corresponding to the financial audit question.

[0048] As shown in Figure 2 The method includes:

[0049] S210, in response to a user input financial audit question, constructing a query target determination prompt word based on historical question and answer information and the financial audit question.

[0050] The historical question and answer information refers to one or more financial audit question and answer examples.

[0051] Exemplarily, the historical question and answer information can include: question 1: "In the photovoltaic power generation prediction project, how to determine the allocation ratio of project funds?", answer 1: "Photovoltaic power generation prediction project file". Question 2: "Use photovoltaic power generation prediction project funds to reimburse the purchase of a hard disk, and the reimbursement amount is 1900", answer 2: "SQL database".

[0052] In the embodiment of the application, the query target determination prompt word refers to reference data for guiding the determination of the query target of the large language model. The query target can be a project file or a SQL database, etc.

[0053] Exemplarily, the query target determination prompt word can be constructed based on the historical question and answer information and the financial audit question by an in-context learning (ICL) method, to help the large language model understand that the financial audit question raised by the user should be queried from which query target.

[0054] S220, inputting the query target determination prompt word into the large language model to obtain a query target corresponding to the financial audit question.

[0055] Exemplarily, the formula for determining the query target corresponding to the financial audit question is:

[0056] C = M(ICL(question));

[0057] Wherein, question represents the financial audit question, ICL(·) represents obtaining the query target determination prompt word by in-context learning, M(·) represents obtaining the query target by the large language model prediction, and C represents the query target, for example, C can be a SQL database or a project file name, etc.

[0058] S230, classifying the query target corresponding to the financial audit question to obtain a task type corresponding to the financial audit question.

[0059] Exemplarily, the query target can be classified by using a decision tree (DT) or other classification algorithm, and the specific mathematical expression is as follows:

[0060] A = DT(C);

[0061] Wherein, C represents a query target, DT(·) represents classification by a decision tree, and A represents a task type corresponding to the financial audit question.

[0062] S240, in the case where the task type corresponding to the financial audit question is a structured query language query task, determining a structured query language query statement corresponding to the financial audit question, executing the structured query language query statement corresponding to the financial audit question, and obtaining a structured query language query result corresponding to the financial audit question.

[0063] S250, in the case where the task type corresponding to the financial audit question is a text understanding task, searching the financial audit question in a financial audit document to obtain associated text corresponding to the financial audit question, and generating a document query result corresponding to the financial audit question based on the associated text corresponding to the financial audit question.

[0064] The technical solution of the embodiment of the present application determines the prompt word based on historical question and answer information and the financial audit question, then inputs the query target determination prompt word into the large language model to obtain the query target corresponding to the financial audit question, and then classifies the query target corresponding to the financial audit question to obtain the task type corresponding to the financial audit question. The above technical solution realizes the determination of the task type corresponding to the financial audit question through the operations of constructing the prompt word, predicting the query target, and classifying, so as to determine whether to go to the SQL database or the financial audit document to find the question answer, thereby improving the financial audit query efficiency.

[0065] Embodiment three

[0066] Figure 3A flowchart of a financial audit method provided for embodiment three of the present application, the method of this embodiment can be combined with each optional scheme in the financial audit method provided in the above embodiments. The financial audit method provided in this embodiment is further optimized. Optionally, determining the structured query language query statement corresponding to the financial audit question comprises: obtaining a plurality of financial audit question samples and a structured query language query statement corresponding to each financial audit question sample; determining the Jaccard similarity of each financial audit question sample and the financial audit question; sorting the plurality of financial audit question samples based on the Jaccard similarity of each financial audit question sample and the financial audit question; based on the sample sorting result, filtering to obtain a financial audit question sample similar to the financial audit question and a structured query language query statement corresponding to the financial audit question sample similar to the financial audit question; constructing a structured query language conversion prompt word based on the financial audit question, the financial audit question sample similar to the financial audit question, and the structured query language query statement corresponding to the financial audit question sample similar to the financial audit question; inputting the structured query language conversion prompt word into a large language model to obtain the structured query language query statement corresponding to the financial audit question.

[0067] As shown in Figure 3 , the method comprises:

[0068] S310, in response to the financial audit question input by the user, determining the task type corresponding to the financial audit question.

[0069] S320, if the task type corresponding to the financial audit question is a structured query language query task, obtaining a plurality of financial audit question samples and a structured query language query statement corresponding to each financial audit question sample.

[0070] Among them, the financial audit question sample is a pre-constructed financial audit question example. The SQL query statement and the financial audit question sample exist in pairs, that is, each financial audit question sample has its corresponding SQL query statement.

[0071] Exemplarily, a plurality of financial audit question samples can be obtained from the QuerytoSQL annotation library, and the financial audit question sample can be: which project of the company in 2024 has the most flow in XX bank. The SQL query statement corresponding to this financial audit question sample is:

[0072] SELECT project name, SUM (transaction amount) AS total amount;

[0073] FROM flow table;

[0074] WHERE bank name = 'XX bank';

[0075] AND YEAR(TRANSDATE)=2024;

[0076] GROUP BY item_name;

[0077] ORDER BY total_amount DESC;

[0078] LIMIT 1.

[0079] S330, determine the Jaccard similarity of each financial audit question example and the financial audit question.

[0080] wherein the Jaccard similarity calculation formula is:

[0081]

[0082] wherein, J i represents the Jaccard similarity of the financial audit question and the i-th financial audit question example, q represents the financial audit question, Q i represents the i-th financial audit question example.

[0083] S340, sort the plurality of financial audit question examples based on the Jaccard similarity of each financial audit question example and the financial audit question; based on the example sorting result, filter to obtain the financial audit question example similar to the financial audit question and the structured query language query statement corresponding to the financial audit question example similar to the financial audit question.

[0084] wherein, the financial audit question example similar to the financial audit question refers to the top k financial audit question examples in the Jaccard similarity of the financial audit question, k is a self-defined parameter value, which is not specifically limited here.

[0085] Exemplarily, based on the Jaccard similarity of each financial audit question example and the financial audit question, the plurality of financial audit question examples are sorted from large to small, the top k financial audit question examples in the example sorting result are taken as the financial audit question examples similar to the financial audit question, and the SQL query statement corresponding to the financial audit question examples similar to the financial audit question is obtained.

[0086] S350, constructing a structured query language conversion prompt word based on the financial audit question, the financial audit question example similar to the financial audit question, and the structured query language query statement corresponding to the financial audit question example similar to the financial audit question.

[0087] wherein, the structured query language conversion prompt word refers to reference data for guiding the generation of SQL statements for large language models.

[0088] Exemplarily, the financial audit question can be: "Query the top 3 items with the most flow in XX bank in 2024?". Similar financial audit question examples can be: "Find the top 2 items with the highest transaction amount in XX bank in 2019", "What is the item with the highest total flow in XX bank in 2021?", "Query the top 5 items with the most flow in XYZ bank in 2021". The SQL query statement corresponding to "Find the top 2 items with the highest transaction amount in XX bank in 2019" is: "SELECT item name, SUM(transaction amount) AS total amount FROM flow WHERE bank name = 'XX bank' AND YEAR(transaction date) = 2019 GROUP BY item name ORDER BY total amount DESC LIMIT 2"; the SQL query statement corresponding to "What is the item with the highest total flow in XX bank in 2021?" is: "SELECT item name, SUM(transaction amount) AS total amount FROM flow table WHERE bank name = 'XX bank' AND YEAR(transaction date) = 2021 GROUP BY item name ORDER BY total amount DESC LIMIT 1"; and the SQL query statement corresponding to "Query the top 5 items with the most flow in XYZ bank in 2021" is: "SELECT item name, SUM(transaction amount) AS total amount FROM flow WHERE bank name = 'XYZ bank' AND YEAR(transaction date) = 2021 GROUP BY item name ORDER BY total amount DESC LIMIT 5".

[0089] Further, the structured query language conversion prompt word can be constructed as:

[0090] "Here are the financial audit questions I want to solve:

[0091] "Query the top 3 items with the most flow in XX bank in 2024?"

[0092] Here are similar questions and their corresponding SQL query statements for reference:

[0093] Similar question 1: "Find the top 2 items with the highest transaction amount in XX bank in 2019";

[0094] The corresponding SQL query statement is: "SELECT item name, SUM(transaction amount) AS total amount FROM flow WHERE bank name = 'XX bank' AND YEAR(transaction date) = 2019 GROUP BY item name ORDER BY total amount DESC LIMIT 2";

[0095] Similar question 2: "Which project has the highest total flow in XX bank in 2021?".

[0096] The corresponding SQL query statement is: "SELECT project name, SUM (transaction amount) AS total amount FROM flow table WHERE bank name = 'XX bank' AND YEAR (transaction date) = 2021 GROUP BY project name ORDER BY total amount DESC LIMIT 1";

[0097] Similar question 3: "Query the top 5 projects with the largest flow in XYZ bank in 2021".

[0098] The corresponding SQL query statement is: "SELECT project name, SUM (transaction amount) AS total amount FROM flow WHERE bank name = 'XYZ bank' AND YEAR (transaction date) = 2021 GROUP BY project name ORDER BY total amount DESC LIMIT 5";

[0099] Please generate appropriate SQL query statements for the financial audit questions based on the above reference.

[0100] S360, input the structured query language conversion prompt word into the large language model, get the structured query language query statement corresponding to the financial audit question, execute the structured query language query statement corresponding to the financial audit question, and get the structured query language query result corresponding to the financial audit question.

[0101] Exemplarily, according to the SQL conversion prompt word, the large language model can output the SQL query statement corresponding to the financial audit question, so as to query in the SQL data using the SQL query statement corresponding to the financial audit question, and obtain the SQL query result.

[0102] In the embodiment of the application, in the case where the task type corresponding to the financial audit question is a text understanding task, the financial audit question is retrieved in the financial audit document to obtain the associated text corresponding to the financial audit question, and the document query result corresponding to the financial audit question is generated based on the associated text corresponding to the financial audit question.

[0103] In some optional embodiments, the execution of the structured query language query statement corresponding to the financial audit question obtains a structured query language query result corresponding to the financial audit question, including: executing the structured query language query statement corresponding to the financial audit question to obtain a plurality of candidate query results; if there are identical candidate query results in the plurality of candidate query results, determining the identical candidate query results as the structured query language query result corresponding to the financial audit question; if there are no identical candidate query results in the plurality of candidate query results, selecting from the plurality of candidate query results based on the Jaccard similarity to obtain the structured query language query result corresponding to the financial audit question.

[0104] Wherein, using the SQL query statement corresponding to the financial audit question in the SQL data query can obtain a plurality of candidate query results, and the candidate query result refers to the SQL query result to be confirmed.

[0105] It should be noted that by judging whether there are identical candidate query results in the plurality of candidate query results, the screening of the candidate query results is realized, so that the accurate and reasonable structured query language query result is determined.

[0106] Exemplarily, the final SQL query result can be determined according to the following formula:

[0107]

[0108] Wherein, Answer represents the structured query language query result corresponding to the financial audit question. a1 represents the identical candidate query result, i.e. the candidate query result with the most occurrences. a2 is the candidate query result of the maximum Jac corresponding example SQL query statement in the SQL database, and Jac represents the Jaccard similarity.

[0109] The technical scheme of the embodiment of the present application obtains a plurality of financial audit question samples and a structured query language query statement corresponding to each financial audit question sample, then determines the Jaccard similarity of each financial audit question sample and a financial audit question, and then sorts the plurality of financial audit question samples based on the Jaccard similarity of each financial audit question sample and the financial audit question. Based on the sample sorting result, the similar financial audit question sample to the financial audit question and the structured query language query statement corresponding to the similar financial audit question sample to the financial audit question are screened, and then the structured query language conversion prompt word is constructed based on the financial audit question, the similar financial audit question sample to the financial audit question, and the structured query language query statement corresponding to the similar financial audit question sample to the financial audit question. The structured query language conversion prompt word is input into the large language model, and the structured query language query statement corresponding to the financial audit question is obtained. The above technical scheme realizes accurate conversion of the SQL query statement through Jaccard similarity sorting and screening, construction of the structured query language conversion prompt word, and prediction of the structured query language query statement, and effectively improves the data query accuracy of the financial audit.

[0110] Embodiment four

[0111] Figure 4 A flowchart of a financial audit method provided by the fourth embodiment of the present application, the method of the present embodiment can be combined with the optional schemes of the financial audit method provided in the above embodiments. The financial audit method provided by the present embodiment is further optimized. Optionally, the financial audit question is retrieved in the financial audit document to obtain the associated text corresponding to the financial audit question, including: performing word segmentation on the financial audit question to obtain the word segmentation result corresponding to the financial audit question; embedding and encoding the word segmentation result corresponding to the financial audit question to obtain the word segmentation semantic vector corresponding to the financial audit question; performing word segmentation on a plurality of text blocks in the financial audit document to obtain the word segmentation result corresponding to each text block; embedding and encoding the word segmentation result corresponding to each text block to obtain the word segmentation semantic vector corresponding to each text block; determining the cosine similarity of the word segmentation semantic vector corresponding to each text block and the word segmentation semantic vector corresponding to the financial audit question; sorting the plurality of text blocks in the financial audit document based on the cosine similarity of the word segmentation semantic vector corresponding to each text block and the word segmentation semantic vector corresponding to the financial audit question; based on the document block sorting result, screening a plurality of text blocks similar to the financial audit question; performing context sorting on the plurality of text blocks similar to the financial audit question to obtain the associated text corresponding to the financial audit question, wherein the associated text is a text having context association.

[0112] As Figure 4As shown, the method comprises:

[0113] S410, in response to the user input financial audit question, determining the task type corresponding to the financial audit question.

[0114] In the embodiment of the application, in the case where the task type corresponding to the financial audit question is a structured query language query task, a structured query language query statement corresponding to the financial audit question is determined, the structured query language query statement corresponding to the financial audit question is executed, and a structured query language query result corresponding to the financial audit question is obtained.

[0115] S420, in the case where the task type corresponding to the financial audit question is a text understanding task, performing word segmentation on the financial audit question to obtain a word segmentation result corresponding to the financial audit question; and performing embedding coding on the word segmentation result corresponding to the financial audit question to obtain a word segmentation semantic vector corresponding to the financial audit question.

[0116] The word segmentation result corresponding to the financial audit question refers to a basic processing unit obtained by decomposing the financial audit question. The word segmentation semantic vector corresponding to the financial audit question is a vector representation of the semantic meaning of the word segmentation result corresponding to the financial audit question.

[0117] Exemplarily, the financial audit question can be segmented by a tokenization layer to obtain a word segmentation result corresponding to the financial audit question, so as to be understood and processed by a large language model, and then the word segmentation result corresponding to the financial audit question is converted into a word segmentation semantic vector corresponding to the financial audit question by an embedding coding layer, so as to perform semantic operation and comparison in a vector space.

[0118] In some optional embodiments, before the word segmentation of the financial audit question, named entity recognition (NER) can also be performed on the financial audit question, so as to obtain target recognition, and then the target recognition is converted into a Json format to obtain a preprocessed financial audit question, and then the preprocessed financial audit question is segmented and embedded coded.

[0119] S430, performing word segmentation on a plurality of text blocks in the financial audit document to obtain a word segmentation result corresponding to each text block; and performing embedding coding on the word segmentation result corresponding to each text block to obtain a word segmentation semantic vector corresponding to each text block.

[0120] The financial audit document can include multiple text blocks, in other words, each text block is a part of the financial audit document. The tokenization result corresponding to the text block refers to the basic processing unit obtained by decomposing the text block. The tokenization semantic vector corresponding to the text block is a vector representation of the semantic meaning of the tokenization result corresponding to the text block.

[0121] Exemplarily, the text block can be tokenized by a tokenization layer to obtain a tokenization result corresponding to the text block, so that the large language model can understand and process, and then the tokenization result corresponding to the text block is converted into a tokenization semantic vector corresponding to the text block by an embedding coding layer, so that semantic operations and comparisons can be performed in a vector space.

[0122] S440, determine the cosine similarity between the tokenization semantic vector corresponding to each text block and the tokenization semantic vector corresponding to the financial audit question; sort the multiple text blocks in the financial audit document based on the cosine similarity between the tokenization semantic vector corresponding to each text block and the tokenization semantic vector corresponding to the financial audit question; and filter to obtain multiple text blocks similar to the financial audit question based on the document block sorting result.

[0123] The text blocks similar to the financial audit question refer to the top m text blocks in the cosine similarity with the financial audit question, and m is a self-defined parameter value, which is not specifically limited herein.

[0124] Exemplarily, the formula for calculating the cosine similarity is as follows:

[0125]

[0126] wherein q' represents the preprocessed financial audit question, D i represents the i-th text block in the financial audit document, C(q', D i ) represents the cosine similarity. Further, the multiple text blocks in the financial audit document are sorted from large to small based on the cosine similarity between the tokenization semantic vector corresponding to each text block and the tokenization semantic vector corresponding to the financial audit question, and the top m text blocks in the document block sorting result are taken as the text blocks similar to the financial audit question.

[0127] S450, context sorting is performed on the multiple text blocks similar to the financial audit question to obtain associated text corresponding to the financial audit question, wherein the associated text is text having context association, and a document query result corresponding to the financial audit question is generated based on the associated text corresponding to the financial audit question.

[0128] Since the text blocks similar to the financial audit problem screened out belong to a static vector and do not change with the context, the document query result generated by the text blocks has the problem of inaccuracy. In the embodiment of the present application, the text blocks similar to the financial audit problem are sorted according to the context to obtain text with context association, and then the document query result is generated by the text with context association, thereby improving the accuracy of the document query result.

[0129] Optionally, the context sorting of the text blocks similar to the financial audit problem obtains the associated text corresponding to the financial audit problem, including: determining the Jaccard similarity of the text blocks similar to the financial audit problem and the financial audit problem; sorting the text blocks similar to the financial audit problem based on the Jaccard similarity of the text blocks similar to the financial audit problem and the financial audit problem; and taking the reordered text blocks similar to the financial audit problem as the associated text corresponding to the financial audit problem.

[0130] Exemplarily, the calculation formula of the associated text is:

[0131]

[0132] wherein q' represents the preprocessed financial audit problem, d i represents the i-th text block similar to the financial audit problem, represents the Jaccard similarity of the i-th text block similar to the financial audit problem and the preprocessed financial audit problem. represents the sorting of d from large to small according to the size of i d' represents the associated text.

[0133] Further, the formula for determining the document query result is:

[0134] Answer = LLM(d');

[0135] wherein LLM(·) represents a large language model, and Answer represents the document query result.

[0136] The technical scheme of the embodiment of the present application obtains the word segmentation result corresponding to the financial audit question by word segmentation on the financial audit question, obtains the word segmentation semantic vector corresponding to the financial audit question by embedding coding on the word segmentation result corresponding to the financial audit question, obtains the word segmentation result corresponding to each text block by word segmentation on the plurality of text blocks in the financial audit document, obtains the word segmentation semantic vector corresponding to each text block by embedding coding on the word segmentation result corresponding to each text block, determines the cosine similarity of the word segmentation semantic vector corresponding to each text block and the word segmentation semantic vector corresponding to the financial audit question, sorts the plurality of text blocks in the financial audit document based on the cosine similarity of the word segmentation semantic vector corresponding to each text block and the word segmentation semantic vector corresponding to the financial audit question, and filters a plurality of text blocks similar to the financial audit question based on the document block sorting result, and performs context sorting on the plurality of text blocks similar to the financial audit question to obtain the associated text corresponding to the financial audit question, wherein the associated text is a text having context association. The above technical scheme realizes the text having context association by word segmentation, embedding coding, cosine similarity sorting and filtering, and context sorting, and effectively improves the reliability and effectiveness of the associated text.

[0137] Embodiment five

[0138] Figure 5 A structural schematic diagram of a financial audit device provided by the embodiment five of the present application is shown in FIG. 5. As shown in the figure, the device comprises: Figure 5

[0139] The financial audit question type determination module 510 is configured to determine the task type corresponding to the financial audit question in response to the financial audit question input by the user.

[0140] The structured query language query result determination module 520 is configured to determine the structured query language query statement corresponding to the financial audit question, execute the structured query language query statement corresponding to the financial audit question, and obtain the structured query language query result corresponding to the financial audit question in the case that the task type corresponding to the financial audit question is a structured query language query task.

[0141] The document query result determination module 530 is configured to retrieve the financial audit question in the financial audit document to obtain the associated text corresponding to the financial audit question in the case that the task type corresponding to the financial audit question is a text understanding task, and generate the document query result corresponding to the financial audit question based on the associated text corresponding to the financial audit question.

[0142] ​The technical scheme of the embodiment of the present application determines the task type corresponding to the financial audit question in response to the user input financial audit question, determines the structured query language query statement corresponding to the financial audit question in the case that the task type corresponding to the financial audit question is a structured query language query task, executes the structured query language query statement corresponding to the financial audit question, and obtains the structured query language query result corresponding to the financial audit question; in the case that the task type corresponding to the financial audit question is a text understanding task, the financial audit question is searched in the financial audit document to obtain the associated text corresponding to the financial audit question, and the document query result corresponding to the financial audit question is generated based on the associated text corresponding to the financial audit question. The above technical scheme classifies the SQL query or the document query based on the user input financial audit question, thereby realizing the quick acquisition of the query result of the financial audit question, and effectively improving the financial audit efficiency.

[0143] In some optional embodiments, the financial audit question type determination module 510 can be specifically used for:

[0144] constructing a query target determination prompt word based on the historical question and answer information and the financial audit question;

[0145] inputting the query target determination prompt word into a large language model to obtain the query target corresponding to the financial audit question;

[0146] classifying the query target corresponding to the financial audit question to obtain the task type corresponding to the financial audit question.

[0147] In some optional embodiments, the structured query language query result determination module 520 comprises:

[0148] a financial audit question sample acquisition unit, configured to acquire a plurality of financial audit question samples and a structured query language query statement corresponding to each financial audit question sample;

[0149] a Jaccard similarity determination unit, configured to determine the Jaccard similarity between each financial audit question sample and the financial audit question;

[0150] a financial audit question sample sorting unit, configured to sort the plurality of financial audit question samples based on the Jaccard similarity between each financial audit question sample and the financial audit question;

[0151] a similar financial audit question sample screening unit, configured to screen, based on the sample sorting result, to obtain a similar financial audit question sample and a structured query language query statement corresponding to the similar financial audit question sample;

[0152] The structured query language conversion prompt word construction unit is configured to construct a structured query language conversion prompt word based on the financial audit question, the financial audit question similar example, and the structured query language query statement corresponding to the financial audit question similar example similar to the financial audit question;

[0153] The structured query language query statement prediction unit is configured to input the structured query language conversion prompt word into a large language model to obtain a structured query language query statement corresponding to the financial audit question.

[0154] In some optional embodiments, the structured query language query result determination module 520 can further include:

[0155] The plurality of candidate query result acquisition units are configured to execute the structured query language query statement corresponding to the financial audit question to obtain a plurality of candidate query results;

[0156] The same candidate query result processing unit is configured to determine the same candidate query result as the structured query language query result corresponding to the financial audit question if there is a same candidate query result in the plurality of candidate query results;

[0157] The different candidate query result processing unit is configured to select, based on a Jaccard similarity, the structured query language query result corresponding to the financial audit question from the plurality of candidate query results if there is no same candidate query result in the plurality of candidate query results.

[0158] In some optional embodiments, the document query result determination module 530 includes:

[0159] The financial audit question segmentation and embedding coding unit is configured to perform segmentation on the financial audit question to obtain a segmentation result corresponding to the financial audit question, and perform embedding coding on the segmentation result corresponding to the financial audit question to obtain a segmentation semantic vector corresponding to the financial audit question;

[0160] The financial audit document segmentation and embedding coding unit is configured to perform segmentation on a plurality of text blocks in a financial audit document to obtain a segmentation result corresponding to each text block, and perform embedding coding on the segmentation result corresponding to each text block to obtain a segmentation semantic vector corresponding to each text block;

[0161] The text block context sorting unit is configured to sort the plurality of text blocks similar to the financial audit question based on the Jaccard similarity of the plurality of text blocks similar to the financial audit question and the financial audit question, and obtain the associated text corresponding to the financial audit question by sorting the plurality of text blocks similar to the financial audit question based on the document block sorting result.

[0162] The text block context sorting unit is configured to sort the plurality of text blocks similar to the financial audit question based on the Jaccard similarity of the plurality of text blocks similar to the financial audit question and the financial audit question, and obtain the associated text corresponding to the financial audit question by sorting the plurality of text blocks similar to the financial audit question based on the document block sorting result.

[0163] In some optional embodiments, the text block context sorting unit can be further configured to:

[0164] determine the Jaccard similarity of the plurality of text blocks similar to the financial audit question and the financial audit question;

[0165] sort the plurality of text blocks similar to the financial audit question based on the Jaccard similarity of the plurality of text blocks similar to the financial audit question and the financial audit question;

[0166] obtain the associated text corresponding to the financial audit question by sorting the plurality of text blocks similar to the financial audit question based on the document block sorting result.

[0167] In some optional embodiments, the document query result determination module 530 can include:

[0168] The audit document retrieval prompt word construction unit is configured to construct an audit document retrieval prompt word based on the financial audit question and the associated text corresponding to the financial audit question.

[0169] The document query result prediction unit is configured to input the audit document retrieval prompt word into a large language model to obtain a document query result corresponding to the financial audit question.

[0170] The financial audit device provided by the embodiments of the present application can execute the financial audit method provided by any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0171] Embodiment six

[0172] Figure 6A structural diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application described and / or claimed in this document.

[0173] As shown, Figure 6 The electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer programs stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An I / O interface 15 is also connected to the bus 14.

[0174] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, speakers, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0175] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as a financial audit method, which includes:

[0176] determining, in response to a financial audit question input by a user, a task type corresponding to the financial audit question;

[0177] In a case where the task type corresponding to the financial audit question is a structured query language query task, a structured query language query statement corresponding to the financial audit question is determined, the structured query language query statement corresponding to the financial audit question is executed, and a structured query language query result corresponding to the financial audit question is obtained;

[0178] In a case where the task type corresponding to the financial audit question is a text understanding task, the financial audit question is searched in a financial audit document to obtain associated text corresponding to the financial audit question, and a document query result corresponding to the financial audit question is generated based on the associated text corresponding to the financial audit question.

[0179] In some embodiments, the financial audit method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded onto RAM 13 and executed by processor 11, one or more steps of the financial audit method described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the financial audit method by any other suitable means, such as by means of firmware.

[0180] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0181] Computer programs for implementing the methods of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, and partially on a remote machine or entirely on a remote machine or server.

[0182] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer-readable storage medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0183] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0184] The systems and techniques described herein can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described herein, or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0185] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0186] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in series, or executed in different orders, as long as the desired results of the technical solutions of the present disclosure can be achieved, and the present disclosure is not limited herein.

[0187] The above detailed description does not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements, and improvements made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method of financial auditing, characterized by, The method comprises the following steps: determining a task type corresponding to a user-input financial audit question; in a case where the task type corresponding to the financial audit question is a structured query language query task, determining a structured query language query statement corresponding to the financial audit question, executing the structured query language query statement corresponding to the financial audit question, and obtaining a structured query language query result corresponding to the financial audit question; in a case where the task type corresponding to the financial audit question is a text understanding task, searching for the financial audit question in a financial audit document to obtain associated text corresponding to the financial audit question, and constructing an audit document search prompt word based on the financial audit question and the associated text corresponding to the financial audit question; wherein the audit document search prompt word is a reference data for guiding the output of an answer by a large language model; inputting the audit document search prompt word into a large language model to obtain a document query result corresponding to the financial audit question; wherein the determination of the task type corresponding to the financial audit question comprises: constructing a query target determination prompt word based on historical question and answer information and the financial audit question; inputting the query target determination prompt word into a large language model to obtain a query target corresponding to the financial audit question; wherein the query target is a project file or an SQL database; classifying the query target corresponding to the financial audit question to obtain the task type corresponding to the financial audit question; the execution of the structured query language query statement corresponding to the financial audit question to obtain the structured query language query result corresponding to the financial audit question comprises: performing SQL statement conversion on the financial audit question to obtain the structured query language query statement corresponding to the financial audit question, executing the structured query language query statement corresponding to the financial audit question, and obtaining a plurality of candidate query results; if there are identical candidate query results in the plurality of candidate query results, determining the identical candidate query results as the structured query language query result corresponding to the financial audit question; if there are no identical candidate query results in the plurality of candidate query results, selecting from the plurality of candidate query results based on Jaccard similarity to obtain the structured query language query result corresponding to the financial audit question.

2. The method of claim 1, wherein, the determination of the structured query language query statement corresponding to the financial audit question comprises: obtaining a plurality of financial audit question samples and a structured query language query statement corresponding to each financial audit question sample; determining the Jaccard similarity between each financial audit question sample and the financial audit question; sorting the plurality of financial audit question samples based on the Jaccard similarity between each financial audit question sample and the financial audit question; based on the sample sorting result, screening to obtain a financial audit question sample similar to the financial audit question and a structured query language query statement corresponding to the financial audit question sample similar to the financial audit question. construct a structured query language conversion prompt word based on the financial audit question, the financial audit question similar to the financial audit question, and a structured query language query statement corresponding to the financial audit question similar to the financial audit question; input the structured query language conversion prompt word into a large language model to obtain a structured query language query statement corresponding to the financial audit question.

3. The method of claim 1, wherein, The retrieving the financial audit question in the financial audit document to obtain the associated text corresponding to the financial audit question comprises: performing word segmentation on the financial audit question to obtain a word segmentation result corresponding to the financial audit question; and performing embedding coding on the word segmentation result corresponding to the financial audit question to obtain a word segmentation semantic vector corresponding to the financial audit question; performing word segmentation on a plurality of text blocks in the financial audit document to obtain a word segmentation result corresponding to each text block; and performing embedding coding on the word segmentation result corresponding to each text block to obtain a word segmentation semantic vector corresponding to each text block; determining a cosine similarity between the word segmentation semantic vector corresponding to each text block and the word segmentation semantic vector corresponding to the financial audit question; sorting the plurality of text blocks in the financial audit document based on the cosine similarity between the word segmentation semantic vector corresponding to each text block and the word segmentation semantic vector corresponding to the financial audit question; filtering to obtain a plurality of text blocks similar to the financial audit question based on the document block sorting result; performing context sorting on the plurality of text blocks similar to the financial audit question to obtain the associated text corresponding to the financial audit question, wherein the associated text is a text having context association.

4. The method of claim 3, wherein, The performing context sorting on the plurality of text blocks similar to the financial audit question to obtain the associated text corresponding to the financial audit question comprises: determining a Jaccard similarity between the plurality of text blocks similar to the financial audit question and the financial audit question; sorting the plurality of text blocks similar to the financial audit question based on the Jaccard similarity between the plurality of text blocks similar to the financial audit question and the financial audit question; taking the plurality of text blocks similar to the financial audit question after being reordered as the associated text corresponding to the financial audit question.

5. A financial auditing apparatus characterized by comprising: comprise: a financial audit question type determination module configured to determine a task type corresponding to a financial audit question in response to the financial audit question input by a user; a structured query language query result determination module configured to, in a case where the task type corresponding to the financial audit question is a structured query language query task, determine a structured query language query statement corresponding to the financial audit question, execute the structured query language query statement corresponding to the financial audit question, and obtain a structured query language query result corresponding to the financial audit question; The document query result determination module is configured to, in a case where the task type corresponding to the financial audit question is a text understanding task, search the financial audit question in a financial audit document to obtain associated text corresponding to the financial audit question, and generate a document query result corresponding to the financial audit question based on the associated text corresponding to the financial audit question. The financial audit question type determination module is specifically configured to: construct a query target determination prompt word based on historical question and answer information and the financial audit question; input the query target determination prompt word into a large language model to obtain a query target corresponding to the financial audit question; the query target is a project file or an SQL database; classify the query target corresponding to the financial audit question to obtain a task type corresponding to the financial audit question. The structured query language query result determination module further includes: a plurality of candidate query result acquisition units configured to perform SQL statement conversion on the financial audit question to obtain a structured query language query statement corresponding to the financial audit question, execute the structured query language query statement corresponding to the financial audit question, and obtain a plurality of candidate query results; a same candidate query result processing unit configured to, if there are same candidate query results in the plurality of candidate query results, determine the same candidate query results as the structured query language query result corresponding to the financial audit question; an unlike candidate query result processing unit configured to, if there are no same candidate query results in the plurality of candidate query results, select, based on a Jaccard similarity, the structured query language query result corresponding to the financial audit question from the plurality of candidate query results. The document query result determination module includes: an audit document search prompt word construction unit configured to construct an audit document search prompt word based on the financial audit question and the associated text corresponding to the financial audit question; the audit document search prompt word is reference data for guiding the output of an answer by a large language model; a document query result prediction unit configured to input the audit document search prompt word into a large language model to obtain a document query result corresponding to the financial audit question.

6. An electronic device, comprising: The electronic device includes: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the financial audit method of any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer instructions for causing a processor to execute the financial audit method of any one of claims 1-4 when executed. The computer readable storage medium stores computer instructions for causing a processor to execute the financial audit method of any one of claims 1-4 when executed.

Images