Accounting processing method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to an accounting processing method and device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring business data; converting the business data into accounting items; the accounting item represents that the accounting element corresponding to the business data changes; the artificial intelligence bookkeeping model constructs corresponding prompt words based on the accounting items; and generating a target accounting document based on the cue word through a large language model. The method can improve the efficiency and reduce the delivery cost of the target accounting document.

Description

Technical Field

[0001] The present application relates to the field of accounting technology, and in particular to an accounting processing method, apparatus, computer equipment, computer-readable storage medium and computer program product. Background Art

[0002] Accounting refers to the recording, calculation and reporting of economic activities of specific entities through confirmation, measurement, recording and reporting, using currency as the main unit of measurement, and providing accounting information required for decision-making to users of relevant accounting information. It is an important part of corporate financial management. Accounting is a very tedious and repetitive job, and accountants must ensure the accuracy of the data.

[0003] The traditional accounting processing method usually configures accounting voucher templates in the computer system, matches business documents with accounting voucher templates, and converts business documents into accounting vouchers. However, voucher templates involve the configuration of more than 20 fields, such as conditions, dates, account values, amounts, unit prices, quantities, exchange rates, etc. The learning cost for business personnel is high and the workload of voucher template configuration is large, which makes the traditional accounting processing method inefficient and high in delivery cost. Summary of the invention

[0004] Based on this, it is necessary to provide an accounting processing method, apparatus, computer equipment, computer-readable storage medium and computer program product that can improve efficiency and reduce delivery costs in response to the above technical problems.

[0005] In a first aspect, the present application provides a bookkeeping processing method, comprising:

[0006] Get business data;

[0007] Converting the business data into accounting events; the accounting events represent changes in accounting elements corresponding to the business data;

[0008] The artificial intelligence accounting model constructs corresponding prompt words based on the accounting matters;

[0009] Generate a target accounting document based on the prompt words through a large language model.

[0010] In one embodiment, the method further comprises:

[0011] Using natural language to describe the item information of the accounting item;

[0012] The artificial intelligence accounting model is configured based on the matter information to obtain the configured artificial intelligence accounting model.

[0013] In one embodiment, the matter information includes accounting matter description information and accounting rule constraint information;

[0014] The artificial intelligence accounting model constructs corresponding prompt words based on the accounting matters, including:

[0015] Obtain accounting document output requirements;

[0016] Through the configured artificial intelligence accounting model, based on the accounting matter description information, the accounting rule constraint information and the accounting voucher output requirements, the prompt words corresponding to the accounting matters are constructed.

[0017] In one embodiment, the generating a target accounting document based on the prompt word by using a large language model includes:

[0018] Determine the mapping relationship between the prompt word and the corresponding document;

[0019] The target accounting document is obtained through a large language model based on the mapping relationship and the prompt word.

[0020] In one embodiment, obtaining the target accounting document based on the mapping relationship and the prompt word through the large language model includes:

[0021] If the mapping relationship is that the prompt word corresponds to an entry in the first document, the prompt word corresponding to each entry in the first document is obtained through the large language model, and the voucher entry description information of the prompt word corresponding to each entry is obtained; and a target accounting voucher corresponding to the first document is generated based on the description information of each voucher entry;

[0022] If the mapping relationship is that the prompt word corresponds to at least two second documents, the voucher description information is obtained based on the prompt word through a large language model, and the voucher description information is split into sub-voucher description information corresponding to each second document; and a target accounting voucher corresponding to the second document is generated based on the sub-voucher description information.

[0023] In one embodiment, converting the business data into accounting matters includes:

[0024] Determining the accounting scenario of the business data;

[0025] Acquire relevant data corresponding to the accounting scenario from the business data;

[0026] The relevant data are converted into corresponding accounting items.

[0027] In a second aspect, the present application also provides an accounting processing device, including:

[0028] Business data acquisition module, used to acquire business data;

[0029] An accounting event acquisition module, used to convert the business data into accounting events; the accounting events represent changes in the accounting elements corresponding to the business data;

[0030] A prompt word construction module is used for the artificial intelligence accounting model to construct corresponding prompt words based on the accounting matters;

[0031] The accounting document generation module is used to generate a target accounting document based on the prompt word through a large language model.

[0032] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0033] Get business data;

[0034] Converting the business data into accounting events; the accounting events represent changes in accounting elements corresponding to the business data;

[0035] The artificial intelligence accounting model constructs corresponding prompt words based on the accounting matters;

[0036] Generate a target accounting document based on the prompt words through a large language model.

[0037] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0038] Get business data;

[0039] Converting the business data into accounting events; the accounting events represent changes in accounting elements corresponding to the business data;

[0040] The artificial intelligence accounting model constructs corresponding prompt words based on the accounting matters;

[0041] Generate a target accounting document based on the prompt words through a large language model.

[0042] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0043] Get business data;

[0044] Converting the business data into accounting events; the accounting events represent changes in accounting elements corresponding to the business data;

[0045] The artificial intelligence accounting model constructs corresponding prompt words based on the accounting matters;

[0046] Generate a target accounting document based on the prompt words through a large language model.

[0047] The above-mentioned accounting processing method, device, computer equipment, computer-readable storage medium and computer program product obtain business data and convert the business data into accounting matters, which represent changes in accounting elements corresponding to the business data; then, the artificial intelligence accounting model can accurately construct corresponding prompt words based on the accounting matters, and can accurately and quickly generate target accounting vouchers based on the prompt words through the large language model, without the need to configure accounting voucher templates, thereby improving the efficiency of generating target accounting vouchers and greatly reducing the delivery cost of generating target accounting vouchers. In addition, in the process of generating the target accounting vouchers, there is no need to compile voucher templates and parse all field values, thereby avoiding the problem of error-proneness in the complex accounting voucher generation process, thereby improving the quality of the target accounting vouchers finally generated and improving the stability of accounting processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 A schematic diagram of a flow chart of an accounting processing method in one embodiment;

[0050] Figure 2 A schematic diagram of converting business data into accounting matters in one embodiment;

[0051] Figure 3 This is an interface diagram of accounting matters in an embodiment;

[0052] Figure 4 A schematic diagram of configuring an artificial intelligence accounting model in one embodiment;

[0053] Figure 5 This is a display interface diagram of an artificial intelligence accounting model in one embodiment;

[0054] Figure 6 A schematic diagram of generating prompt words in one embodiment;

[0055] Figure 7 A schematic diagram of converting voucher entry description information into a target accounting voucher in an embodiment;

[0056] Figure 8 A flowchart of an accounting processing method in another embodiment;

[0057] Fig. 9 is a structural block diagram of an accounting processing device in an embodiment;

[0058] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0060] In one embodiment, Figure 1 As shown, a bookkeeping processing method is provided. This embodiment uses the method applied to a computer device as an example for illustration. The computer device can be a terminal or a server. It can be understood that the method can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0061] In this embodiment, the accounting processing method includes the following steps:

[0062] Step S102, obtaining business data.

[0063] The business data refers to the accounting data related to bookkeeping. The form of business data is not limited, and can be business documents, pictures, text, Excel tables, PDF or heterogeneous data.

[0064] Optionally, the computer device obtains business data for different accounting scenarios.

[0065] Optionally, the computer device uses at least one thread to obtain business data, which can improve the performance of generating target accounting documents; each thread corresponds to a document and an account book. The account book is the main body of accounting, and different organizations need to create different account books. The same organization can create multiple account books according to different accounting purposes.

[0066] Step S104, converting the business data into accounting events; accounting events represent changes in accounting elements corresponding to the business data.

[0067] Among them, accounting events are events that cause changes in accounting elements. For example, a purchase advance payment of 100,000 yuan paid to supplier A on June 19, 2024 will cause changes in accounting element assets. The accounting event may be a decrease in bank deposits or an increase in prepaid accounts.

[0068] Optionally, converting the business data into accounting matters includes: determining an accounting scenario for the business data; obtaining relevant data corresponding to the accounting scenario from the business data; and converting the relevant data into corresponding accounting matters.

[0069] Among them, the accounting scenario is the scenario corresponding to the accounting of the business data. Exemplarily, the accounting scenario can be one of the following: purchase of fixed assets, asset depreciation, asset disposal, receipt and delivery of purchased goods, payment of purchase funds, receipt of sales proceeds, etc. If the accounting scenario is the purchase of fixed assets, then the relevant data corresponding to the accounting scenario of the purchase of fixed assets is obtained, including asset category, acquisition method, supplier, original value of assets, etc. Based on the relevant data, the applicable conditions, source fields and business descriptions can be determined, thereby generating accounting matters including applicable conditions, source fields and business descriptions.

[0070] It is understandable that business data is stored in business documents, and there may be some fields on the business documents that are irrelevant to the accounting scenario. If the data corresponding to the irrelevant fields are converted into accounting matters and subsequently input into the large language model for processing, the accuracy of the accounting documents output by the large language model will be reduced. Therefore, extracting corresponding relevant data according to different accounting scenarios, such as the relevant data corresponding to the accounting scenario of purchasing fixed assets, can further improve the accuracy of generating the target accounting documents.

[0071] Optionally, the business data carries an accounting scenario, and the computer device determines the accounting scenario from the business data.

[0072] Optionally, the computer device determines the applicable conditions, source fields and business descriptions of relevant data corresponding to the accounting scenario, and generates accounting matters including the applicable conditions, source fields and business descriptions.

[0073] It is understandable that because there may be multiple accounting scenarios for a business document, the applicable conditions are used to distinguish different accounting scenarios; the source field is the business data such as the field on the document that needs to be input into the artificial intelligence accounting model; the business description is the description of the source field, which is input into the artificial intelligence accounting model to improve the understanding ability of the artificial intelligence accounting model.

[0074] like Figure 2 As shown, the computer device obtains business data, which can be in the form of business documents, pictures, text, Excel tables, PDF or heterogeneous data; if the business data is in the form of business documents, that is, ERP system data, then the business data is directly taken to generate accounting items; if the business data is in the form of pictures, text, Excel tables or PDF, the business data is input into the large language model, converted into ERP system data (accounting items) through the external data model, and then the voucher is generated, so that the original data can be traced; if the business data is in the form of heterogeneous data, that is, the heterogeneous data exists in other systems, that is, external data, the ERP system data (accounting items) is generated through the API interface, and then the voucher is generated, so that the original data can be traced. Among them, the ERP system is an information system with management accounting as the core. Among them, the external data model is a metadata table used to store external data, and external data (specific data) is generated after the external data is introduced.

[0075] like Figure 3 The figure shows the interface diagram of accounting matters. In the interface diagram of accounting matters, accounting matters include basic information, basic information of accounting matters and source of accounting matter entries.

[0076] Step S106, the artificial intelligence accounting model constructs corresponding prompt words based on accounting matters.

[0077] The AI ​​accounting model is a model for accounting with AI (Artificial Intelligence). The prompt is information used to instruct the generation of a target accounting document.

[0078] Optionally, the artificial intelligence accounting model is configured according to accounting matters to obtain a configured artificial intelligence accounting model; and corresponding prompt words are constructed based on accounting matters through the configured artificial intelligence accounting model.

[0079] Optionally, the computer device configures the accounting parameters of the artificial intelligence accounting model according to the accounting matters to obtain the configured artificial intelligence accounting model, and constructs prompt words corresponding to the accounting matters through the configured accounting parameters in the configured artificial intelligence accounting model.

[0080] Among them, the accounting parameters include accounting matter parameters and accounting rule constraint parameters. The accounting matter parameters can configure accounting matter information, and the accounting rule constraint parameters can configure accounting rule constraint information.

[0081] Optionally, computer equipment can configure the accounting rules in the AI ​​accounting model according to different accounting matters, such as various entry rules such as account range and summary, which can improve the accuracy of AI accounting and meet the accounting needs of different enterprises.

[0082] Step S108, generating a target accounting voucher based on the prompt word through a large language model.

[0083] Among them, the target accounting voucher refers to the written proof of the occurrence or completion of the economic business of the business data, which is the basis for registering the account book. The large language model (LLM) refers to a deep learning model trained with a large amount of text data, which can generate natural language text or understand the meaning of language text.

[0084] Optionally, the computer device calls a large language model, inputs the prompt word into the large language model, and converts the prompt word into a target accounting document through the large language model.

[0085] Optionally, the computer device outputs voucher description information based on the prompt word through the large language model, and generates a target accounting voucher based on the voucher description information. The voucher description information is used to describe the target accounting voucher and can instruct the large language model to generate the target accounting voucher.

[0086] The above-mentioned accounting processing method obtains business data and converts the business data into accounting matters, which represent changes in accounting elements corresponding to the business data. Then, the artificial intelligence accounting model can accurately construct corresponding prompt words based on the accounting matters, and can accurately and quickly generate target accounting vouchers based on the prompt words through the large language model. There is no need to configure accounting voucher templates, which improves the efficiency of generating target accounting vouchers and greatly reduces the delivery cost of generating target accounting vouchers. In addition, in the process of generating the target accounting vouchers, there is no need to compile voucher templates and parse all field values, which avoids the problem that the complex accounting voucher generation process is prone to errors, thereby improving the quality of the target accounting vouchers finally generated and improving the stability of accounting processing.

[0087] In addition, the above-mentioned accounting processing method improves accounting efficiency: it is ready to use out of the box and automatically adapts to changes in business, subjects and accounting dimensions; reduces learning costs: accounting rules are described in natural language, and financial personnel only need to understand the company's accounting rules to complete accounting work; reduces operating costs: financial personnel can adjust the artificial intelligence accounting model by themselves, or generate accounting models through artificial intelligence; solves the problem of overseas accounting difficulties: being proficient in the languages ​​​​and accounting standards of multiple countries can ensure the standardization and consistency of the company's accounting processing at home and abroad.

[0088] With the financial knowledge and understanding ability of the general big language model, the business data can be passed to the big language model, which will automatically identify the accounting scenario, extract relevant data, and output the target accounting documents in a predetermined format that comply with the company's accounting rules.

[0089] In one embodiment, the above method also includes: using natural language to describe the matter information of the accounting matter; configuring the artificial intelligence accounting model based on the matter information to obtain the configured artificial intelligence accounting model.

[0090] Among them, the event information may include at least one of the accounting event description information and the accounting rule constraint information, the accounting event description information includes at least one of the accounting scenario description information, the accounting event business information description and the business value field value, and the accounting rule constraint information includes at least one of the entry rule description, the full name of the underlying detailed account and the account rule description. The configured artificial intelligence accounting model complies with the national accounting standards.

[0091] Optionally, the computer device obtains a user's customized adjustment instruction, and adjusts the configured artificial intelligence accounting model based on the customized adjustment instruction to obtain a new configured artificial intelligence accounting model.

[0092] Optionally, the matter information includes accounting matter description information and accounting rule constraint information; the artificial intelligence accounting model constructs corresponding prompt words based on the accounting matters, including: obtaining accounting voucher output requirements; through the configured artificial intelligence accounting model, based on the accounting matter description information, accounting rule constraint information and accounting voucher output requirements, construct prompt words corresponding to the accounting matters.

[0093] The accounting document output requirement is a pre-set fixed content, and the accounting document output requirement includes at least one of an output target, an output format, constraints, and an execution process.

[0094] Optionally, the computer device combines the accounting matter description information, accounting rule constraint information and accounting voucher output requirements through the configured artificial intelligence accounting model to obtain the prompt words corresponding to the accounting matters.

[0095] In this embodiment, the computer device uses natural language to describe the matter information of accounting matters, and configures the artificial intelligence accounting model based on the matter information. The configured artificial intelligence accounting model can be obtained quickly and accurately. Users can use it out of the box without configuring accounting voucher templates, which greatly reduces the delivery cost of generating target accounting vouchers.

[0096] Furthermore, the computer device obtains the accounting voucher output requirements, and generates prompt words corresponding to the accounting matters through the configured artificial intelligence accounting model based on the accounting matter description information, accounting rule constraint information and accounting voucher output requirements, thereby guiding the large language model to output target accounting vouchers for different scenarios and different ledgers, thereby improving accuracy.

[0097] In one embodiment, Figure 4 As shown, the computer device obtains the enterprise accounting rules, which may include text, pictures, Excel, Word, PDF or historical vouchers, etc.; the enterprise accounting rules are input into the large language model, and the large language model can interpret the enterprise accounting rules based on the industry knowledge base, the enterprise knowledge base and the RAG knowledge base, configure the artificial intelligence accounting model, and obtain the configured artificial intelligence accounting model. The computer device can also preset the artificial intelligence accounting model, and then configure the preset artificial intelligence accounting model. The computer device can also customize the artificial intelligence accounting model.

[0098] The configured artificial intelligence accounting model includes accounting matter description information, accounting rule constraint information and accounting voucher output requirements. The accounting matter description information includes accounting scenario description information, accounting matter business information description and business value field value. The accounting rule constraint information includes entry rule description information, the full name of the underlying detailed account and account rule description information.

[0099] like Figure 5 Shown is a display interface diagram of the artificial intelligence accounting model. In the display interface diagram, the artificial intelligence accounting model includes basic information and detailed description of voucher entries, and may also include configuration help information for configuring the artificial intelligence accounting model.

[0100] In one embodiment, generating a target accounting voucher based on prompt words through a large language model includes: determining a mapping relationship between the prompt words and the corresponding documents; and obtaining the target accounting voucher based on the mapping relationship and the prompt words through the large language model.

[0101] The mapping relationship between the prompt word and the corresponding document may be that the prompt word corresponds to an entry in the first document, or the prompt word corresponds to at least two second documents.

[0102] Optionally, the computer device determines the document identifier in the prompt word. If the document identifier indicates that the prompt word is a prompt word obtained from an entry in the first document, that is, the first document is split according to each entry, and each entry obtains a prompt word; if the prompt word includes at least two document identifiers, it indicates that the prompt word is a prompt word generated after merging multiple documents.

[0103] Optionally, a target accounting voucher is obtained based on a mapping relationship and a prompt word through a large language model, including: if the mapping relationship is that the prompt word corresponds to an entry in a first document, then the prompt word corresponding to each entry in the first document is obtained through the large language model, and the voucher entry description information of the prompt word corresponding to each entry is obtained; based on the description information of each voucher entry, a target accounting voucher corresponding to the first document is generated; if the mapping relationship is that the prompt word corresponds to at least two second documents, then the voucher description information is obtained based on the prompt word through the large language model, and the voucher description information is split into sub-voucher description information corresponding to each second document; and the target accounting voucher corresponding to the second document is generated based on the sub-voucher description information.

[0104] The voucher entry description information includes at least one of the document ID, summary, debit / credit direction, account, currency, original currency amount, base currency amount, and source document entry ID. The voucher description information includes at least one of the document ID, summary, debit / credit direction, account, currency, original currency amount, and base currency amount.

[0105] Optionally, if the mapping relationship is that the prompt word corresponds to the entry in the first document, the prompt word corresponding to each entry in the first document is obtained through the large language model according to the identifier of the first document, and the voucher entry description information corresponding to each prompt word is generated based on the prompt word corresponding to each entry; and each voucher entry description information is converted into a target accounting voucher corresponding to the first document.

[0106] Optionally, if the mapping relationship is that the prompt word corresponds to at least two second documents, the prompt word is converted into voucher description information through a large language model, and the voucher description information is split into sub-voucher description information corresponding to each second document according to the identifiers of at least two second documents; for each sub-voucher description information, the sub-voucher description information is converted into a target accounting voucher corresponding to the second document.

[0107] In this embodiment, the computer device determines the mapping relationship between the prompt word and the corresponding document, and can accurately obtain the target accounting document based on the mapping relationship and the prompt word through the large language model.

[0108] Furthermore, the computer device can accurately generate a target accounting voucher corresponding to each document according to the specific mapping relationship between the prompt word and the document.

[0109] In one embodiment, Figure 6The figure shows a schematic diagram of generating prompt words. The computer device performs AI accounting on the business data to obtain the configured artificial intelligence accounting model. The configured artificial intelligence accounting model includes accounting matter description information, accounting rule constraint information and accounting voucher output requirements. The accounting matter description information includes accounting scenario description information, accounting matter business information description and business value field value. The accounting rule constraint information includes entry rule description information, the full name of the underlying detailed account and account rule description information; the prompt words corresponding to the accounting matters are constructed through the configured artificial intelligence accounting model; the prompt words are input into the large language model, and the voucher entry description information is output based on the prompt words through the large language model, and the voucher entry description information is converted into the target accounting voucher.

[0110] like Figure 7 The figure shows a schematic diagram of converting voucher entry description information into a target accounting voucher. The computing device obtains the voucher entry description information and converts each voucher entry description information into a target accounting voucher. In the interface diagram of the target accounting voucher of the DRT system, the target accounting voucher includes 6 sub-vouchers, and each sub-voucher corresponds to a voucher entry description information.

[0111] In one embodiment, Figure 8 As shown, the computer device obtains business data, which can be in the form of business documents, pictures, texts, voices, Excel tables, PDFs or heterogeneous data; extracts accounting data (related data) from the business data, such as document fields, basic information, amounts, etc., and converts the related data into accounting matters; describes the matter information of accounting matters in natural language, and the matter information includes accounting matter description information and accounting rule constraint information, and the accounting rule constraint information includes accounting constraint matters (such as account scope, accounting rule description, etc.); obtains accounting voucher output requirements and output requirements (such as roles, targets and output formats, etc.); configures the artificial intelligence accounting model according to accounting matters, and generates prompt words corresponding to accounting matters based on the accounting matter description information, accounting rule constraint information and accounting voucher output requirements through the configured artificial intelligence accounting model and AI development platform (prompt word API, knowledge base); obtains voucher entry description information in JSON format based on the prompt words through the large language model, performs accounting check on the voucher entry description information, and converts the voucher entry description information into the target accounting voucher after the check passes. Computer equipment can also generate voucher reports and voucher modification records based on target accounting vouchers. Among them, the AI ​​development platform is an AI application development platform, such as building intelligent entities, prompt words, task flows, knowledge bases, etc., to provide better support for business.

[0112] In one embodiment, a billing processing method is also provided, which is applied to a computer device, and the billing processing method includes the following steps:

[0113] Step A1: Obtain business data.

[0114] Step A2: determine the accounting scenario of the business data.

[0115] Step A3, obtaining relevant data corresponding to the accounting scenario from the business data.

[0116] Step A4, converting the relevant data into corresponding accounting events; accounting events represent changes in accounting elements corresponding to business data.

[0117] Step A5, using natural language to describe the item information of the accounting item; the item information includes the accounting item description information and the accounting rule constraint information.

[0118] Step A6, configure the artificial intelligence accounting model based on the matter information to obtain the configured artificial intelligence accounting model.

[0119] Step A7, obtaining accounting document output requirements.

[0120] Step A8, through the configured artificial intelligence accounting model, based on the accounting matter description information, accounting rule constraint information and accounting voucher output requirements, construct the prompt words corresponding to the accounting matters.

[0121] Step A9, determining the mapping relationship between the prompt word and the corresponding document.

[0122] Step A10, if the mapping relationship is that the prompt word corresponds to the entry in the first document, the prompt word corresponding to each entry in the first document is obtained through the large language model, and the voucher entry description information of the prompt word corresponding to each entry is obtained; based on the description information of each voucher entry, a target accounting voucher corresponding to the first document is generated; if the mapping relationship is that the prompt word corresponds to at least two second documents, the voucher description information is obtained based on the prompt word through the large language model, and the voucher description information is split into sub-voucher description information corresponding to each second document; based on the sub-voucher description information, a target accounting voucher corresponding to the second document is generated.

[0123] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0124] Based on the same inventive concept, the embodiment of the present application also provides an accounting processing device for implementing the accounting processing method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more accounting processing device embodiments provided below can refer to the limitations of the accounting processing method above, and will not be repeated here.

[0125] In an exemplary embodiment, Fig. 9 As shown, an accounting processing device is provided, including: a business data acquisition module 902, an accounting event acquisition module 904, a prompt word construction module 906 and an accounting voucher generation module 908, wherein:

[0126] The business data acquisition module 902 is used to acquire business data.

[0127] The accounting event acquisition module 904 is used to convert business data into accounting events; accounting events represent changes in accounting elements corresponding to business data.

[0128] The prompt word construction module 906 is used for the artificial intelligence accounting model to construct corresponding prompt words based on accounting matters.

[0129] The accounting voucher generation module 908 is used to generate a target accounting voucher based on the prompt words through a large language model.

[0130] The above-mentioned accounting processing device obtains business data and converts the business data into accounting matters, which represent changes in accounting elements corresponding to the business data. Then, the artificial intelligence accounting model can accurately construct corresponding prompt words based on the accounting matters, and can accurately and quickly generate target accounting vouchers based on the prompt words through the large language model. There is no need to configure accounting voucher templates, which improves the efficiency of generating target accounting vouchers and greatly reduces the delivery cost of generating target accounting vouchers. In addition, in the process of generating the target accounting vouchers, there is no need to compile voucher templates and parse all field values, which avoids the problem of error-proneness in the complex accounting voucher generation process, thereby improving the quality of the target accounting vouchers finally generated and improving the stability of accounting processing.

[0131] In one embodiment, the above-mentioned device also includes an artificial intelligence accounting model configuration module, which is used to describe the matter information of accounting matters in natural language; configure the artificial intelligence accounting model based on the matter information to obtain the configured artificial intelligence accounting model.

[0132] In one embodiment, the matter information includes accounting matter description information and accounting rule constraint information; the above-mentioned prompt word construction module 906 is also used to obtain accounting voucher output requirements; through the configured artificial intelligence accounting model, based on the accounting matter description information, accounting rule constraint information and accounting voucher output requirements, construct the prompt words corresponding to the accounting matters.

[0133] In one embodiment, the accounting voucher generation module 908 is further used to determine the mapping relationship between the prompt word and the corresponding document; and obtain the target accounting voucher based on the mapping relationship and the prompt word through the large language model.

[0134] In one embodiment, the accounting voucher generation module 908 is also used to obtain the prompt words corresponding to each entry in the first document through a large language model if the mapping relationship is that the prompt word corresponds to an entry in the first document, and obtain the voucher entry description information of the prompt word corresponding to each entry; generate a target accounting voucher corresponding to the first document based on each voucher entry description information; if the mapping relationship is that the prompt word corresponds to at least two second documents, obtain the voucher description information based on the prompt word through a large language model, and split the voucher description information into sub-voucher description information corresponding to each second document; generate a target accounting voucher corresponding to the second document based on the sub-voucher description information.

[0135] In one embodiment, the accounting event acquisition module 904 is further used to determine the accounting scenario of the business data; acquire relevant data corresponding to the accounting scenario from the business data; and convert the relevant data into corresponding accounting events.

[0136] Each module in the above-mentioned accounting processing device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0137] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Fig.10 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a bookkeeping processing method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0138] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0139] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0140] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0141] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0142] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0143] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0144] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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 application.

[0145] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A bookkeeping processing method, characterized in that: The method comprises: Get business data; Converting the business data into accounting events; the accounting events represent changes in accounting elements corresponding to the business data; The artificial intelligence accounting model constructs corresponding prompt words based on the accounting matters; Generate a target accounting document based on the prompt words through a large language model.

2. The method according to claim 1, characterized in that The method further comprises: Using natural language to describe the item information of the accounting item; The artificial intelligence accounting model is configured based on the matter information to obtain the configured artificial intelligence accounting model.

3. The method according to claim 2, characterized in that The item information includes accounting item description information and accounting rule constraint information; The artificial intelligence accounting model constructs corresponding prompt words based on the accounting matters, including: Obtain accounting document output requirements; Through the configured artificial intelligence accounting model, based on the accounting matter description information, the accounting rule constraint information and the accounting voucher output requirements, the prompt words corresponding to the accounting matters are constructed.

4. The method according to claim 1, characterized in that: The generating a target accounting voucher based on the prompt word by using a large language model includes: Determine the mapping relationship between the prompt word and the corresponding document; The target accounting document is obtained through a large language model based on the mapping relationship and the prompt word.

5. The method according to claim 4, characterized in that The step of obtaining a target accounting document based on the mapping relationship and the prompt word through a large language model includes: If the mapping relationship is that the prompt word corresponds to an entry in the first document, the prompt word corresponding to each entry in the first document is obtained through the large language model, and the voucher entry description information of the prompt word corresponding to each entry is obtained; and a target accounting voucher corresponding to the first document is generated based on the description information of each voucher entry; If the mapping relationship is that the prompt word corresponds to at least two second documents, the voucher description information is obtained based on the prompt word through a large language model, and the voucher description information is split into sub-voucher description information corresponding to each second document; and a target accounting voucher corresponding to the second document is generated based on the sub-voucher description information.

6. The method according to claim 1, characterized in that The converting of the business data into accounting matters comprises: Determining the accounting scenario of the business data; Acquire relevant data corresponding to the accounting scenario from the business data; The relevant data are converted into corresponding accounting items.

7. An accounting processing device, characterized in that: The device comprises: Business data acquisition module, used to acquire business data; An accounting event acquisition module, used to convert the business data into accounting events; the accounting events represent changes in the accounting elements corresponding to the business data; A prompt word construction module is used for the artificial intelligence accounting model to construct corresponding prompt words based on the accounting matters; The accounting document generation module is used to generate a target accounting document based on the prompt word through a large language model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images